danvics/haiku.rag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge pull request #308 from ggozad/feat/rlm-monty-update

Browse source 
RLM monty update.
This commit is contained in:
Yiorgis Gozadinos 2026-03-13 11:23:39 +02:00 committed by GitHub
commit b09b45e8fa
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
14 changed files with 2805 additions and 4690 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
CHANGELOG.md
View file

@ -1,6 +1,10 @@
# Changelog # Changelog
## [Unreleased] ## [Unreleased]
### Changed
- **RLM sandbox**: Bumped pydantic-monty to 0.0.8. Removed `regex_*` external functions — the sandbox now has native `re` and `math` modules via `import`. Also adds `filter()` and `getattr()` builtins.
## [0.33.3] - 2026-03-12 ## [0.33.3] - 2026-03-12
### Added ### Added

7
docs/agents/rlm.md
View file

@ -64,15 +64,14 @@ The agent's code runs in a sandboxed Python interpreter ([pydantic-monty](https:
| `get_chunk(chunk_id)` | Get a chunk with metadata (headings, page numbers, labels) for citations | | `get_chunk(chunk_id)` | Get a chunk with metadata (headings, page numbers, labels) for citations |
| `get_docling_document(document_id)` | Get the full DoclingDocument structure as a dict (texts, tables, pictures, pages) | | `get_docling_document(document_id)` | Get the full DoclingDocument structure as a dict (texts, tables, pictures, pages) |
| `llm(prompt)` | Call an LLM for classification, summarization, or extraction | | `llm(prompt)` | Call an LLM for classification, summarization, or extraction |
| `regex_findall(pattern, text)`, `regex_sub(pattern, repl, text)`, `regex_search(pattern, text)`, `regex_split(pattern, text)` | Regular expression matching via Python's `re` module |
When documents are pre-loaded via the `documents` parameter, they are injected as a `documents` variable accessible in the sandbox code. When documents are pre-loaded via the `documents` parameter, they are injected as a `documents` variable accessible in the sandbox code.
### Python Features ### Python Features
The interpreter supports a subset of Python: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, try/except, and the `json` module. The interpreter supports a subset of Python: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `filter()`, `getattr()`, try/except, and the `json`, `re`, `math` modules.
Not supported: imports (other than `json`), class definitions, generators/yield, match statements, decorators, `with` statements. For pattern matching, the agent can use the `regex_*` functions, string methods, or the `llm()` function. Not supported: most imports (only `json`, `re`, `math` are available), class definitions, generators/yield, match statements, decorators, `with` statements. For pattern matching, the agent can use `import re`, string methods, or the `llm()` function.
### Security ### Security
@ -80,7 +79,7 @@ Code executes in an isolated interpreter with:
- **No filesystem access**: Code cannot read or write files - **No filesystem access**: Code cannot read or write files
- **No network access**: Code cannot make HTTP requests or open sockets - **No network access**: Code cannot make HTTP requests or open sockets
- **No imports**: Only the `json` module is available - **No imports**: Only `json`, `re`, and `math` modules are available
- **Execution timeout**: Configurable limit (default 60s) - **Execution timeout**: Configurable limit (default 60s)
- **Output truncation**: Large outputs are truncated to prevent memory issues - **Output truncation**: Large outputs are truncated to prevent memory issues

21
haiku_rag_slim/haiku/rag/agents/rlm/prompts.py
View file

@ -34,18 +34,6 @@ Use `list_documents()` or search results to get document IDs first.
- `pictures`: list of figures/images with metadata - `pictures`: list of figures/images with metadata
- `pages`: page dimensions and metadata - `pages`: page dimensions and metadata
### await regex_findall(pattern, text) -> list[str]
Find all non-overlapping matches of a regular expression pattern in text.
### await regex_sub(pattern, repl, text) -> str
Replace all occurrences of a regular expression pattern with a replacement string.
### await regex_search(pattern, text) -> dict | None
Search for the first match of a pattern. Returns a dict with keys: group, groups, start, end — or None if no match.
### await regex_split(pattern, text) -> list[str]
Split text by a regular expression pattern.
### await llm(prompt) -> str ### await llm(prompt) -> str
Call an LLM directly with the given prompt. Returns the response as a string. Call an LLM directly with the given prompt. Returns the response as a string.
Use this for classification, summarization, extraction, or any task where you Use this for classification, summarization, extraction, or any task where you
@ -63,11 +51,11 @@ Check if it exists with: `try: documents ... except NameError: ...`
## Available Python Features ## Available Python Features
The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `sorted()`/`.sort(key=...)`, try/except, and the `json` module. The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `filter()`, `getattr()`, `sorted()`/`.sort(key=...)`, try/except, and the `json`, `re`, `math` modules.
Not supported: imports (other than `json`), class definitions, generators/yield, match statements, decorators, `with` statements. Not supported: most imports (only `json`, `re`, `math` are available), class definitions, generators/yield, match statements, decorators, `with` statements.
For pattern matching or text extraction, use the `regex_*` functions, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function. For pattern matching or text extraction, use `import re`, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function.
## Strategy Guide ## Strategy Guide
@ -93,10 +81,11 @@ print(f"Total: {count}")
### Extracting data with regex ### Extracting data with regex
```python ```python
import re
numbers = [] numbers = []
results = await search("financial data", limit=20) results = await search("financial data", limit=20)
for r in results: for r in results:
amounts = await regex_findall(r'\\$([\\d,]+)', r['content']) amounts = re.findall(r'\\$([\\d,]+)', r['content'])
for a in amounts: for a in amounts:
numbers.append(int(a.replace(',', ''))) numbers.append(int(a.replace(',', '')))
if numbers: if numbers:

26
haiku_rag_slim/haiku/rag/agents/rlm/sandbox.py
View file

@ -1,5 +1,4 @@
import json import json
import re
from dataclasses import dataclass from dataclasses import dataclass
from typing import TYPE_CHECKING, Any, Literal from typing import TYPE_CHECKING, Any, Literal
@ -128,26 +127,6 @@ class Sandbox:
result = await agent.run(prompt) result = await agent.run(prompt)
return result.output return result.output
async def regex_findall(pattern: str, text: str) -> list[str]:
return re.findall(pattern, text)
async def regex_sub(pattern: str, repl: str, text: str) -> str:
return re.sub(pattern, repl, text)
async def regex_search(pattern: str, text: str) -> dict[str, Any] | None:
m = re.search(pattern, text)
if m is None:
return None
return {
"group": m.group(),
"groups": list(m.groups()),
"start": m.start(),
"end": m.end(),
}
async def regex_split(pattern: str, text: str) -> list[str]:
return re.split(pattern, text)
return { return {
"search": search, "search": search,
"list_documents": list_documents, "list_documents": list_documents,
@ -155,10 +134,6 @@ class Sandbox:
"get_chunk": get_chunk, "get_chunk": get_chunk,
"get_docling_document": get_docling_document, "get_docling_document": get_docling_document,
"llm": llm, "llm": llm,
"regex_findall": regex_findall,
"regex_sub": regex_sub,
"regex_search": regex_search,
"regex_split": regex_split,
} }
async def execute(self, code: str) -> SandboxResult: async def execute(self, code: str) -> SandboxResult:
@ -185,7 +160,6 @@ class Sandbox:
monty = pydantic_monty.Monty( monty = pydantic_monty.Monty(
code, code,
inputs=input_names, inputs=input_names,
external_functions=list(external_fns.keys()),
) )
except ( except (
pydantic_monty.MontySyntaxError, pydantic_monty.MontySyntaxError,

2
haiku_rag_slim/pyproject.toml
View file

@ -31,7 +31,7 @@ dependencies = [
"pathspec>=1.0.4", "pathspec>=1.0.4",
"pydantic>=2.12.5", "pydantic>=2.12.5",
"pydantic-ai-slim[openai,fastmcp,logfire,ag-ui]>=1.66.0", "pydantic-ai-slim[openai,fastmcp,logfire,ag-ui]>=1.66.0",
"pydantic-monty>=0.0.7", "pydantic-monty>=0.0.8",
"python-dotenv>=1.2.2", "python-dotenv>=1.2.2",
"pyyaml>=6.0.3", "pyyaml>=6.0.3",
"rich>=14.3.3", "rich>=14.3.3",

64
tests/agents/rlm/test_sandbox.py
View file

@ -381,70 +381,6 @@ class TestSandboxDoclingDocument:
assert "True" in result.stdout assert "True" in result.stdout
class TestSandboxRegex:
"""Test regex external functions."""
@pytest.mark.asyncio
async def test_regex_findall(self, sandbox):
"""regex_findall extracts all matches."""
result = await sandbox.execute(
r"matches = await regex_findall(r'\d+', 'abc 123 def 456')"
"\nprint(matches)"
)
assert result.success
assert "['123', '456']" in result.stdout
@pytest.mark.asyncio
async def test_regex_sub(self, sandbox):
"""regex_sub replaces matches."""
result = await sandbox.execute(
r"out = await regex_sub(r'\d+', 'X', 'abc 123 def 456')"
"\nprint(out)"
)
assert result.success
assert "abc X def X" in result.stdout
@pytest.mark.asyncio
async def test_regex_search_match(self, sandbox):
"""regex_search returns match dict when pattern matches."""
result = await sandbox.execute(
r"m = await regex_search(r'(\d+)', 'abc 123')"
"\nprint(m['group'])"
"\nprint(m['start'])"
"\nprint(m['end'])"
)
assert result.success
assert "123" in result.stdout
assert "4" in result.stdout
assert "7" in result.stdout
@pytest.mark.asyncio
async def test_regex_search_no_match(self, sandbox):
"""regex_search returns None when pattern doesn't match."""
result = await sandbox.execute(
r"m = await regex_search(r'\d+', 'abc')"
"\nprint(m is None)"
)
assert result.success
assert "True" in result.stdout
@pytest.mark.asyncio
async def test_regex_split(self, sandbox):
"""regex_split splits on pattern."""
result = await sandbox.execute(
"out = await regex_split(',', 'a,b,,c')\nprint(out)"
)
assert result.success
assert "['a', 'b', '', 'c']" in result.stdout
@pytest.mark.asyncio
async def test_regex_invalid_pattern(self, sandbox):
"""Invalid regex pattern surfaces as an error."""
result = await sandbox.execute("await regex_findall('[invalid', 'text')")
assert not result.success
assert result.stderr != ""
class TestSandboxLLM: class TestSandboxLLM:
"""Test llm() external function.""" """Test llm() external function."""

515
tests/cassettes/test_rlm/TestClientRLMIntegration.test_rlm_aggregation.yaml
View file

@ -128,7 +128,7 @@ interactions:
connection: connection:
- keep-alive - keep-alive
content-length: content-length:
- '7737' - '7274'
content-type: content-type:
- application/json - application/json
host: host:
@ -173,18 +173,6 @@ interactions:
- `pictures`: list of figures/images with metadata - `pictures`: list of figures/images with metadata
- `pages`: page dimensions and metadata - `pages`: page dimensions and metadata
### await regex_findall(pattern, text) -> list[str]
Find all non-overlapping matches of a regular expression pattern in text.
### await regex_sub(pattern, repl, text) -> str
Replace all occurrences of a regular expression pattern with a replacement string.
### await regex_search(pattern, text) -> dict | None
Search for the first match of a pattern. Returns a dict with keys: group, groups, start, end — or None if no match.
### await regex_split(pattern, text) -> list[str]
Split text by a regular expression pattern.
### await llm(prompt) -> str ### await llm(prompt) -> str
Call an LLM directly with the given prompt. Returns the response as a string. Call an LLM directly with the given prompt. Returns the response as a string.
Use this for classification, summarization, extraction, or any task where you Use this for classification, summarization, extraction, or any task where you
@ -202,11 +190,11 @@ interactions:
## Available Python Features ## Available Python Features
The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `sorted()`/`.sort(key=...)`, try/except, and the `json` module. The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `filter()`, `getattr()`, `sorted()`/`.sort(key=...)`, try/except, and the `json`, `re`, `math` modules.
Not supported: imports (other than `json`), class definitions, generators/yield, match statements, decorators, `with` statements. Not supported: most imports (only `json`, `re`, `math` are available), class definitions, generators/yield, match statements, decorators, `with` statements.
For pattern matching or text extraction, use the `regex_*` functions, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function. For pattern matching or text extraction, use `import re`, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function.
## Strategy Guide ## Strategy Guide
@ -232,10 +220,11 @@ interactions:
### Extracting data with regex ### Extracting data with regex
```python ```python
import re
numbers = [] numbers = []
results = await search("financial data", limit=20) results = await search("financial data", limit=20)
for r in results: for r in results:
amounts = await regex_findall(r'\$([\d,]+)', r['content']) amounts = re.findall(r'\$([\d,]+)', r['content'])
for a in amounts: for a in amounts:
numbers.append(int(a.replace(',', ''))) numbers.append(int(a.replace(',', '')))
if numbers: if numbers:
@ -296,6 +285,7 @@ interactions:
strict: true strict: true
type: json_schema type: json_schema
stream: false stream: false
temperature: 0.0
tool_choice: auto tool_choice: auto
tools: tools:
- function: - function:
@ -325,7 +315,7 @@ interactions:
response: response:
headers: headers:
content-length: content-length:
- '690' - '699'
content-type: content-type:
- application/json - application/json
parsed_body: parsed_body:
@ -334,25 +324,26 @@ interactions:
index: 0 index: 0
message: message:
content: '' content: ''
reasoning: Need revenue from quarterly reports. Search for "quarterly report revenue". reasoning: Need to search for quarterly reports revenue.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor arguments: '{"code":"import re\n# search for revenue in quarterly reports\nresults = await search(\"quarterly
r in results[:5]:\n print(r[''document_title''], r[''score''], r[''content''][:200])"}' report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''],
r[''score''])\n"}'
name: execute_code name: execute_code
id: call_no1egdsi id: call_exbbulxp
index: 0 index: 0
type: function type: function
created: 1772626955 created: 1773329130
id: chatcmpl-2 id: chatcmpl-407
model: gpt-oss model: gpt-oss
object: chat.completion object: chat.completion
system_fingerprint: fp_ollama system_fingerprint: fp_ollama
usage: usage:
completion_tokens: 85 completion_tokens: 85
prompt_tokens: 1688 prompt_tokens: 1594
total_tokens: 1773 total_tokens: 1679
status: status:
code: 200 code: 200
message: OK message: OK
@ -405,7 +396,7 @@ interactions:
connection: connection:
- keep-alive - keep-alive
content-length: content-length:
- '8682' - '8148'
content-type: content-type:
- application/json - application/json
host: host:
@ -450,18 +441,6 @@ interactions:
- `pictures`: list of figures/images with metadata - `pictures`: list of figures/images with metadata
- `pages`: page dimensions and metadata - `pages`: page dimensions and metadata
### await regex_findall(pattern, text) -> list[str]
Find all non-overlapping matches of a regular expression pattern in text.
### await regex_sub(pattern, repl, text) -> str
Replace all occurrences of a regular expression pattern with a replacement string.
### await regex_search(pattern, text) -> dict | None
Search for the first match of a pattern. Returns a dict with keys: group, groups, start, end — or None if no match.
### await regex_split(pattern, text) -> list[str]
Split text by a regular expression pattern.
### await llm(prompt) -> str ### await llm(prompt) -> str
Call an LLM directly with the given prompt. Returns the response as a string. Call an LLM directly with the given prompt. Returns the response as a string.
Use this for classification, summarization, extraction, or any task where you Use this for classification, summarization, extraction, or any task where you
@ -479,11 +458,11 @@ interactions:
## Available Python Features ## Available Python Features
The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `sorted()`/`.sort(key=...)`, try/except, and the `json` module. The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `filter()`, `getattr()`, `sorted()`/`.sort(key=...)`, try/except, and the `json`, `re`, `math` modules.
Not supported: imports (other than `json`), class definitions, generators/yield, match statements, decorators, `with` statements. Not supported: most imports (only `json`, `re`, `math` are available), class definitions, generators/yield, match statements, decorators, `with` statements.
For pattern matching or text extraction, use the `regex_*` functions, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function. For pattern matching or text extraction, use `import re`, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function.
## Strategy Guide ## Strategy Guide
@ -509,10 +488,11 @@ interactions:
### Extracting data with regex ### Extracting data with regex
```python ```python
import re
numbers = [] numbers = []
results = await search("financial data", limit=20) results = await search("financial data", limit=20)
for r in results: for r in results:
amounts = await regex_findall(r'\$([\d,]+)', r['content']) amounts = re.findall(r'\$([\d,]+)', r['content'])
for a in amounts: for a in amounts:
numbers.append(int(a.replace(',', ''))) numbers.append(int(a.replace(',', '')))
if numbers: if numbers:
@ -552,21 +532,20 @@ interactions:
- content: What is the total revenue across all quarterly reports? - content: What is the total revenue across all quarterly reports?
role: user role: user
- content: null - content: null
reasoning: Need revenue from quarterly reports. Search for "quarterly report revenue". reasoning: Need to search for quarterly reports revenue.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor arguments: '{"code":"import re\n# search for revenue in quarterly reports\nresults = await search(\"quarterly
r in results[:5]:\n print(r[''document_title''], r[''score''], r[''content''][:200])"}' report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''], r[''score''])\n"}'
name: execute_code name: execute_code
id: call_no1egdsi id: call_exbbulxp
type: function type: function
- content: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''], - content: '{"code":"import re\n# search for revenue in quarterly reports\nresults = await search(\"quarterly report
r[''score''], r[''content''][:200])","stdout":"3\nQ1 Report 0.03226645663380623 Sales report Q1: Revenue was $100,000.\nQ2 revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''], r[''score''])\n","stdout":"3\nQ1
Report 0.03226645663380623 Sales report Q2: Revenue was $150,000.\nQ3 Report 0.032258063554763794 Sales report Q3: Report 0.03226645663380623\nQ2 Report 0.03226645663380623\nQ3 Report 0.032258063554763794\n","stderr":"","success":true}'
Revenue was $200,000.\n","stderr":"","success":true}'
role: tool role: tool
tool_call_id: call_no1egdsi tool_call_id: call_exbbulxp
model: gpt-oss model: gpt-oss
reasoning_effort: low reasoning_effort: low
response_format: response_format:
@ -589,6 +568,7 @@ interactions:
strict: true strict: true
type: json_schema type: json_schema
stream: false stream: false
temperature: 0.0
tool_choice: auto tool_choice: auto
tools: tools:
- function: - function:
@ -618,7 +598,7 @@ interactions:
response: response:
headers: headers:
content-length: content-length:
- '689' - '680'
content-type: content-type:
- application/json - application/json
parsed_body: parsed_body:
@ -627,25 +607,25 @@ interactions:
index: 0 index: 0
message: message:
content: '' content: ''
reasoning: Three reports with revenue numbers. Sum = 450k. Need citation chunks. Retrieve chunks. reasoning: We need revenue numbers. Let's fetch chunks.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"chunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''], arguments: '{"code":"# get chunks for each result\nchunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''],
chunk[''content''].strip())"}' chunk[''content''][:200])\n"}'
name: execute_code name: execute_code
id: call_sg5vtxpb id: call_2hd3mgon
index: 0 index: 0
type: function type: function
created: 1772626957 created: 1773329146
id: chatcmpl-37 id: chatcmpl-173
model: gpt-oss model: gpt-oss
object: chat.completion object: chat.completion
system_fingerprint: fp_ollama system_fingerprint: fp_ollama
usage: usage:
completion_tokens: 85 completion_tokens: 85
prompt_tokens: 1922 prompt_tokens: 1798
total_tokens: 2007 total_tokens: 1883
status: status:
code: 200 code: 200
message: OK message: OK
@ -658,7 +638,7 @@ interactions:
connection: connection:
- keep-alive - keep-alive
content-length: content-length:
- '9437' - '8925'
content-type: content-type:
- application/json - application/json
host: host:
@ -703,18 +683,6 @@ interactions:
- `pictures`: list of figures/images with metadata - `pictures`: list of figures/images with metadata
- `pages`: page dimensions and metadata - `pages`: page dimensions and metadata
### await regex_findall(pattern, text) -> list[str]
Find all non-overlapping matches of a regular expression pattern in text.
### await regex_sub(pattern, repl, text) -> str
Replace all occurrences of a regular expression pattern with a replacement string.
### await regex_search(pattern, text) -> dict | None
Search for the first match of a pattern. Returns a dict with keys: group, groups, start, end — or None if no match.
### await regex_split(pattern, text) -> list[str]
Split text by a regular expression pattern.
### await llm(prompt) -> str ### await llm(prompt) -> str
Call an LLM directly with the given prompt. Returns the response as a string. Call an LLM directly with the given prompt. Returns the response as a string.
Use this for classification, summarization, extraction, or any task where you Use this for classification, summarization, extraction, or any task where you
@ -732,11 +700,11 @@ interactions:
## Available Python Features ## Available Python Features
The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `sorted()`/`.sort(key=...)`, try/except, and the `json` module. The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `filter()`, `getattr()`, `sorted()`/`.sort(key=...)`, try/except, and the `json`, `re`, `math` modules.
Not supported: imports (other than `json`), class definitions, generators/yield, match statements, decorators, `with` statements. Not supported: most imports (only `json`, `re`, `math` are available), class definitions, generators/yield, match statements, decorators, `with` statements.
For pattern matching or text extraction, use the `regex_*` functions, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function. For pattern matching or text extraction, use `import re`, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function.
## Strategy Guide ## Strategy Guide
@ -762,10 +730,11 @@ interactions:
### Extracting data with regex ### Extracting data with regex
```python ```python
import re
numbers = [] numbers = []
results = await search("financial data", limit=20) results = await search("financial data", limit=20)
for r in results: for r in results:
amounts = await regex_findall(r'\$([\d,]+)', r['content']) amounts = re.findall(r'\$([\d,]+)', r['content'])
for a in amounts: for a in amounts:
numbers.append(int(a.replace(',', ''))) numbers.append(int(a.replace(',', '')))
if numbers: if numbers:
@ -805,35 +774,34 @@ interactions:
- content: What is the total revenue across all quarterly reports? - content: What is the total revenue across all quarterly reports?
role: user role: user
- content: null - content: null
reasoning: Need revenue from quarterly reports. Search for "quarterly report revenue". reasoning: Need to search for quarterly reports revenue.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor arguments: '{"code":"import re\n# search for revenue in quarterly reports\nresults = await search(\"quarterly
r in results[:5]:\n print(r[''document_title''], r[''score''], r[''content''][:200])"}' report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''], r[''score''])\n"}'
name: execute_code name: execute_code
id: call_no1egdsi id: call_exbbulxp
type: function type: function
- content: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''], - content: '{"code":"import re\n# search for revenue in quarterly reports\nresults = await search(\"quarterly report
r[''score''], r[''content''][:200])","stdout":"3\nQ1 Report 0.03226645663380623 Sales report Q1: Revenue was $100,000.\nQ2 revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''], r[''score''])\n","stdout":"3\nQ1
Report 0.03226645663380623 Sales report Q2: Revenue was $150,000.\nQ3 Report 0.032258063554763794 Sales report Q3: Report 0.03226645663380623\nQ2 Report 0.03226645663380623\nQ3 Report 0.032258063554763794\n","stderr":"","success":true}'
Revenue was $200,000.\n","stderr":"","success":true}'
role: tool role: tool
tool_call_id: call_no1egdsi tool_call_id: call_exbbulxp
- content: null - content: null
reasoning: Three reports with revenue numbers. Sum = 450k. Need citation chunks. Retrieve chunks. reasoning: We need revenue numbers. Let's fetch chunks.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"chunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''], arguments: '{"code":"# get chunks for each result\nchunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''],
chunk[''content''].strip())"}' chunk[''content''][:200])\n"}'
name: execute_code name: execute_code
id: call_sg5vtxpb id: call_2hd3mgon
type: function type: function
- content: '{"code":"chunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''], - content: '{"code":"# get chunks for each result\nchunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''],
chunk[''content''].strip())","stdout":"","stderr":"NameError: name ''results'' is not defined","success":false}' chunk[''content''][:200])\n","stdout":"","stderr":"NameError: name ''results'' is not defined","success":false}'
role: tool role: tool
tool_call_id: call_sg5vtxpb tool_call_id: call_2hd3mgon
model: gpt-oss model: gpt-oss
reasoning_effort: low reasoning_effort: low
response_format: response_format:
@ -856,6 +824,7 @@ interactions:
strict: true strict: true
type: json_schema type: json_schema
stream: false stream: false
temperature: 0.0
tool_choice: auto tool_choice: auto
tools: tools:
- function: - function:
@ -885,7 +854,7 @@ interactions:
response: response:
headers: headers:
content-length: content-length:
- '737' - '713'
content-type: content-type:
- application/json - application/json
parsed_body: parsed_body:
@ -894,25 +863,25 @@ interactions:
index: 0 index: 0
message: message:
content: '' content: ''
reasoning: Need to keep results variable. Use same scope. Let's re-run with storing results. reasoning: Need to re-run search inside same code.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n c arguments: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n chunk
= await get_chunk(r[''chunk_id''])\n chunks.append(c)\n print(c[''document_title''], c[''content''].strip())"}' = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''], chunk[''content''][:200])\n"}'
name: execute_code name: execute_code
id: call_h6pfbenb id: call_10n40kz9
index: 0 index: 0
type: function type: function
created: 1772626960 created: 1773329159
id: chatcmpl-20 id: chatcmpl-749
model: gpt-oss model: gpt-oss
object: chat.completion object: chat.completion
system_fingerprint: fp_ollama system_fingerprint: fp_ollama
usage: usage:
completion_tokens: 98 completion_tokens: 93
prompt_tokens: 2084 prompt_tokens: 1970
total_tokens: 2182 total_tokens: 2063
status: status:
code: 200 code: 200
message: OK message: OK
@ -965,7 +934,7 @@ interactions:
connection: connection:
- keep-alive - keep-alive
content-length: content-length:
- '10405' - '9885'
content-type: content-type:
- application/json - application/json
host: host:
@ -1010,18 +979,6 @@ interactions:
- `pictures`: list of figures/images with metadata - `pictures`: list of figures/images with metadata
- `pages`: page dimensions and metadata - `pages`: page dimensions and metadata
### await regex_findall(pattern, text) -> list[str]
Find all non-overlapping matches of a regular expression pattern in text.
### await regex_sub(pattern, repl, text) -> str
Replace all occurrences of a regular expression pattern with a replacement string.
### await regex_search(pattern, text) -> dict | None
Search for the first match of a pattern. Returns a dict with keys: group, groups, start, end — or None if no match.
### await regex_split(pattern, text) -> list[str]
Split text by a regular expression pattern.
### await llm(prompt) -> str ### await llm(prompt) -> str
Call an LLM directly with the given prompt. Returns the response as a string. Call an LLM directly with the given prompt. Returns the response as a string.
Use this for classification, summarization, extraction, or any task where you Use this for classification, summarization, extraction, or any task where you
@ -1039,11 +996,11 @@ interactions:
## Available Python Features ## Available Python Features
The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `sorted()`/`.sort(key=...)`, try/except, and the `json` module. The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `filter()`, `getattr()`, `sorted()`/`.sort(key=...)`, try/except, and the `json`, `re`, `math` modules.
Not supported: imports (other than `json`), class definitions, generators/yield, match statements, decorators, `with` statements. Not supported: most imports (only `json`, `re`, `math` are available), class definitions, generators/yield, match statements, decorators, `with` statements.
For pattern matching or text extraction, use the `regex_*` functions, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function. For pattern matching or text extraction, use `import re`, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function.
## Strategy Guide ## Strategy Guide
@ -1069,10 +1026,11 @@ interactions:
### Extracting data with regex ### Extracting data with regex
```python ```python
import re
numbers = [] numbers = []
results = await search("financial data", limit=20) results = await search("financial data", limit=20)
for r in results: for r in results:
amounts = await regex_findall(r'\$([\d,]+)', r['content']) amounts = re.findall(r'\$([\d,]+)', r['content'])
for a in amounts: for a in amounts:
numbers.append(int(a.replace(',', ''))) numbers.append(int(a.replace(',', '')))
if numbers: if numbers:
@ -1112,51 +1070,50 @@ interactions:
- content: What is the total revenue across all quarterly reports? - content: What is the total revenue across all quarterly reports?
role: user role: user
- content: null - content: null
reasoning: Need revenue from quarterly reports. Search for "quarterly report revenue". reasoning: Need to search for quarterly reports revenue.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor arguments: '{"code":"import re\n# search for revenue in quarterly reports\nresults = await search(\"quarterly
r in results[:5]:\n print(r[''document_title''], r[''score''], r[''content''][:200])"}' report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''], r[''score''])\n"}'
name: execute_code name: execute_code
id: call_no1egdsi id: call_exbbulxp
type: function type: function
- content: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''], - content: '{"code":"import re\n# search for revenue in quarterly reports\nresults = await search(\"quarterly report
r[''score''], r[''content''][:200])","stdout":"3\nQ1 Report 0.03226645663380623 Sales report Q1: Revenue was $100,000.\nQ2 revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''], r[''score''])\n","stdout":"3\nQ1
Report 0.03226645663380623 Sales report Q2: Revenue was $150,000.\nQ3 Report 0.032258063554763794 Sales report Q3: Report 0.03226645663380623\nQ2 Report 0.03226645663380623\nQ3 Report 0.032258063554763794\n","stderr":"","success":true}'
Revenue was $200,000.\n","stderr":"","success":true}'
role: tool role: tool
tool_call_id: call_no1egdsi tool_call_id: call_exbbulxp
- content: null - content: null
reasoning: Three reports with revenue numbers. Sum = 450k. Need citation chunks. Retrieve chunks. reasoning: We need revenue numbers. Let's fetch chunks.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"chunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''], arguments: '{"code":"# get chunks for each result\nchunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''],
chunk[''content''].strip())"}' chunk[''content''][:200])\n"}'
name: execute_code name: execute_code
id: call_sg5vtxpb id: call_2hd3mgon
type: function type: function
- content: '{"code":"chunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''], - content: '{"code":"# get chunks for each result\nchunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''],
chunk[''content''].strip())","stdout":"","stderr":"NameError: name ''results'' is not defined","success":false}' chunk[''content''][:200])\n","stdout":"","stderr":"NameError: name ''results'' is not defined","success":false}'
role: tool role: tool
tool_call_id: call_sg5vtxpb tool_call_id: call_2hd3mgon
- content: null - content: null
reasoning: Need to keep results variable. Use same scope. Let's re-run with storing results. reasoning: Need to re-run search inside same code.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n c arguments: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n chunk
= await get_chunk(r[''chunk_id''])\n chunks.append(c)\n print(c[''document_title''], c[''content''].strip())"}' = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''], chunk[''content''][:200])\n"}'
name: execute_code name: execute_code
id: call_h6pfbenb id: call_10n40kz9
type: function type: function
- content: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n c - content: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n chunk
= await get_chunk(r[''chunk_id''])\n chunks.append(c)\n print(c[''document_title''], c[''content''].strip())","stdout":"Q1 = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''], chunk[''content''][:200])\n","stdout":"Q1
Report Sales report Q1: Revenue was $100,000.\nQ2 Report Sales report Q2: Revenue was $150,000.\nQ3 Report Sales Report Sales report Q1: Revenue was $100,000.\nQ2 Report Sales report Q2: Revenue was $150,000.\nQ3 Report Sales
report Q3: Revenue was $200,000.\n","stderr":"","success":true}' report Q3: Revenue was $200,000.\n","stderr":"","success":true}'
role: tool role: tool
tool_call_id: call_h6pfbenb tool_call_id: call_10n40kz9
model: gpt-oss model: gpt-oss
reasoning_effort: low reasoning_effort: low
response_format: response_format:
@ -1179,6 +1136,7 @@ interactions:
strict: true strict: true
type: json_schema type: json_schema
stream: false stream: false
temperature: 0.0
tool_choice: auto tool_choice: auto
tools: tools:
- function: - function:
@ -1208,7 +1166,7 @@ interactions:
response: response:
headers: headers:
content-length: content-length:
- '614' - '643'
content-type: content-type:
- application/json - application/json
parsed_body: parsed_body:
@ -1216,25 +1174,26 @@ interactions:
- finish_reason: tool_calls - finish_reason: tool_calls
index: 0 index: 0
message: message:
content: Now compute sum. content: ''
reasoning: Sum revenues.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"total = 0\nfor c in chunks:\n nums = await regex_findall(r''\\$([\\d,]+)'', c[''content''])\n for arguments: '{"code":"total=0\nfor c in chunks:\n import re\n m=re.search(r''\\$([\\d,]+)'', c[''content''])\n if
n in nums:\n total += int(n.replace('','', ''''))\nprint(total)"}' m:\n val=int(m.group(1).replace('','',''''))\n total+=val\nprint(total)\n"}'
name: execute_code name: execute_code
id: call_rlqh271l id: call_51jmnwfv
index: 0 index: 0
type: function type: function
created: 1772626962 created: 1773329170
id: chatcmpl-924 id: chatcmpl-461
model: gpt-oss model: gpt-oss
object: chat.completion object: chat.completion
system_fingerprint: fp_ollama system_fingerprint: fp_ollama
usage: usage:
completion_tokens: 83 completion_tokens: 88
prompt_tokens: 2312 prompt_tokens: 2196
total_tokens: 2395 total_tokens: 2284
status: status:
code: 200 code: 200
message: OK message: OK
@ -1247,7 +1206,7 @@ interactions:
connection: connection:
- keep-alive - keep-alive
content-length: content-length:
- '11090' - '10618'
content-type: content-type:
- application/json - application/json
host: host:
@ -1292,18 +1251,6 @@ interactions:
- `pictures`: list of figures/images with metadata - `pictures`: list of figures/images with metadata
- `pages`: page dimensions and metadata - `pages`: page dimensions and metadata
### await regex_findall(pattern, text) -> list[str]
Find all non-overlapping matches of a regular expression pattern in text.
### await regex_sub(pattern, repl, text) -> str
Replace all occurrences of a regular expression pattern with a replacement string.
### await regex_search(pattern, text) -> dict | None
Search for the first match of a pattern. Returns a dict with keys: group, groups, start, end — or None if no match.
### await regex_split(pattern, text) -> list[str]
Split text by a regular expression pattern.
### await llm(prompt) -> str ### await llm(prompt) -> str
Call an LLM directly with the given prompt. Returns the response as a string. Call an LLM directly with the given prompt. Returns the response as a string.
Use this for classification, summarization, extraction, or any task where you Use this for classification, summarization, extraction, or any task where you
@ -1321,11 +1268,11 @@ interactions:
## Available Python Features ## Available Python Features
The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `sorted()`/`.sort(key=...)`, try/except, and the `json` module. The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `filter()`, `getattr()`, `sorted()`/`.sort(key=...)`, try/except, and the `json`, `re`, `math` modules.
Not supported: imports (other than `json`), class definitions, generators/yield, match statements, decorators, `with` statements. Not supported: most imports (only `json`, `re`, `math` are available), class definitions, generators/yield, match statements, decorators, `with` statements.
For pattern matching or text extraction, use the `regex_*` functions, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function. For pattern matching or text extraction, use `import re`, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function.
## Strategy Guide ## Strategy Guide
@ -1351,10 +1298,11 @@ interactions:
### Extracting data with regex ### Extracting data with regex
```python ```python
import re
numbers = [] numbers = []
results = await search("financial data", limit=20) results = await search("financial data", limit=20)
for r in results: for r in results:
amounts = await regex_findall(r'\$([\d,]+)', r['content']) amounts = re.findall(r'\$([\d,]+)', r['content'])
for a in amounts: for a in amounts:
numbers.append(int(a.replace(',', ''))) numbers.append(int(a.replace(',', '')))
if numbers: if numbers:
@ -1394,65 +1342,65 @@ interactions:
- content: What is the total revenue across all quarterly reports? - content: What is the total revenue across all quarterly reports?
role: user role: user
- content: null - content: null
reasoning: Need revenue from quarterly reports. Search for "quarterly report revenue". reasoning: Need to search for quarterly reports revenue.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor arguments: '{"code":"import re\n# search for revenue in quarterly reports\nresults = await search(\"quarterly
r in results[:5]:\n print(r[''document_title''], r[''score''], r[''content''][:200])"}' report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''], r[''score''])\n"}'
name: execute_code name: execute_code
id: call_no1egdsi id: call_exbbulxp
type: function type: function
- content: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''], - content: '{"code":"import re\n# search for revenue in quarterly reports\nresults = await search(\"quarterly report
r[''score''], r[''content''][:200])","stdout":"3\nQ1 Report 0.03226645663380623 Sales report Q1: Revenue was $100,000.\nQ2 revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''], r[''score''])\n","stdout":"3\nQ1
Report 0.03226645663380623 Sales report Q2: Revenue was $150,000.\nQ3 Report 0.032258063554763794 Sales report Q3: Report 0.03226645663380623\nQ2 Report 0.03226645663380623\nQ3 Report 0.032258063554763794\n","stderr":"","success":true}'
Revenue was $200,000.\n","stderr":"","success":true}'
role: tool role: tool
tool_call_id: call_no1egdsi tool_call_id: call_exbbulxp
- content: null - content: null
reasoning: Three reports with revenue numbers. Sum = 450k. Need citation chunks. Retrieve chunks. reasoning: We need revenue numbers. Let's fetch chunks.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"chunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''], arguments: '{"code":"# get chunks for each result\nchunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''],
chunk[''content''].strip())"}' chunk[''content''][:200])\n"}'
name: execute_code name: execute_code
id: call_sg5vtxpb id: call_2hd3mgon
type: function type: function
- content: '{"code":"chunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''], - content: '{"code":"# get chunks for each result\nchunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''],
chunk[''content''].strip())","stdout":"","stderr":"NameError: name ''results'' is not defined","success":false}' chunk[''content''][:200])\n","stdout":"","stderr":"NameError: name ''results'' is not defined","success":false}'
role: tool role: tool
tool_call_id: call_sg5vtxpb tool_call_id: call_2hd3mgon
- content: null - content: null
reasoning: Need to keep results variable. Use same scope. Let's re-run with storing results. reasoning: Need to re-run search inside same code.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n c arguments: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n chunk
= await get_chunk(r[''chunk_id''])\n chunks.append(c)\n print(c[''document_title''], c[''content''].strip())"}' = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''], chunk[''content''][:200])\n"}'
name: execute_code name: execute_code
id: call_h6pfbenb id: call_10n40kz9
type: function type: function
- content: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n c - content: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n chunk
= await get_chunk(r[''chunk_id''])\n chunks.append(c)\n print(c[''document_title''], c[''content''].strip())","stdout":"Q1 = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''], chunk[''content''][:200])\n","stdout":"Q1
Report Sales report Q1: Revenue was $100,000.\nQ2 Report Sales report Q2: Revenue was $150,000.\nQ3 Report Sales Report Sales report Q1: Revenue was $100,000.\nQ2 Report Sales report Q2: Revenue was $150,000.\nQ3 Report Sales
report Q3: Revenue was $200,000.\n","stderr":"","success":true}' report Q3: Revenue was $200,000.\n","stderr":"","success":true}'
role: tool role: tool
tool_call_id: call_h6pfbenb tool_call_id: call_10n40kz9
- content: Now compute sum. - content: null
reasoning: Sum revenues.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"total = 0\nfor c in chunks:\n nums = await regex_findall(r''\\$([\\d,]+)'', c[''content''])\n for arguments: '{"code":"total=0\nfor c in chunks:\n import re\n m=re.search(r''\\$([\\d,]+)'', c[''content''])\n if
n in nums:\n total += int(n.replace('','', ''''))\nprint(total)"}' m:\n val=int(m.group(1).replace('','',''''))\n total+=val\nprint(total)\n"}'
name: execute_code name: execute_code
id: call_rlqh271l id: call_51jmnwfv
type: function type: function
- content: '{"code":"total = 0\nfor c in chunks:\n nums = await regex_findall(r''\\$([\\d,]+)'', c[''content''])\n for - content: '{"code":"total=0\nfor c in chunks:\n import re\n m=re.search(r''\\$([\\d,]+)'', c[''content''])\n if
n in nums:\n total += int(n.replace('','', ''''))\nprint(total)","stdout":"","stderr":"NameError: name ''chunks'' m:\n val=int(m.group(1).replace('','',''''))\n total+=val\nprint(total)\n","stdout":"","stderr":"NameError:
is not defined","success":false}' name ''chunks'' is not defined","success":false}'
role: tool role: tool
tool_call_id: call_rlqh271l tool_call_id: call_51jmnwfv
model: gpt-oss model: gpt-oss
reasoning_effort: low reasoning_effort: low
response_format: response_format:
@ -1475,6 +1423,7 @@ interactions:
strict: true strict: true
type: json_schema type: json_schema
stream: false stream: false
temperature: 0.0
tool_choice: auto tool_choice: auto
tools: tools:
- function: - function:
@ -1504,7 +1453,7 @@ interactions:
response: response:
headers: headers:
content-length: content-length:
- '819' - '848'
content-type: content-type:
- application/json - application/json
parsed_body: parsed_body:
@ -1513,27 +1462,26 @@ interactions:
index: 0 index: 0
message: message:
content: '' content: ''
reasoning: Variable scope lost. Let's combine. reasoning: Need to keep chunks variable. Let's combine.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n c arguments: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n chunk
= await get_chunk(r[''chunk_id''])\n chunks.append(c)\n\ntotal = 0\nfor c in chunks:\n nums = await = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n\ntotal=0\nimport re\nfor c in chunks:\n m=re.search(r''\\$([\\d,]+)'',
regex_findall(r''\\$([\\d,]+)'', c[''content''])\n for n in nums:\n total += int(n.replace('','', c[''content''])\n if m:\n val=int(m.group(1).replace('','',''''))\n total+=val\nprint(total)\n"}'
''''))\nprint(total)"}'
name: execute_code name: execute_code
id: call_kbsx3dxm id: call_axsiusi8
index: 0 index: 0
type: function type: function
created: 1772626965 created: 1773329179
id: chatcmpl-319 id: chatcmpl-56
model: gpt-oss model: gpt-oss
object: chat.completion object: chat.completion
system_fingerprint: fp_ollama system_fingerprint: fp_ollama
usage: usage:
completion_tokens: 132 completion_tokens: 140
prompt_tokens: 2483 prompt_tokens: 2380
total_tokens: 2615 total_tokens: 2520
status: status:
code: 200 code: 200
message: OK message: OK
@ -1586,7 +1534,7 @@ interactions:
connection: connection:
- keep-alive - keep-alive
content-length: content-length:
- '12120' - '11699'
content-type: content-type:
- application/json - application/json
host: host:
@ -1631,18 +1579,6 @@ interactions:
- `pictures`: list of figures/images with metadata - `pictures`: list of figures/images with metadata
- `pages`: page dimensions and metadata - `pages`: page dimensions and metadata
### await regex_findall(pattern, text) -> list[str]
Find all non-overlapping matches of a regular expression pattern in text.
### await regex_sub(pattern, repl, text) -> str
Replace all occurrences of a regular expression pattern with a replacement string.
### await regex_search(pattern, text) -> dict | None
Search for the first match of a pattern. Returns a dict with keys: group, groups, start, end — or None if no match.
### await regex_split(pattern, text) -> list[str]
Split text by a regular expression pattern.
### await llm(prompt) -> str ### await llm(prompt) -> str
Call an LLM directly with the given prompt. Returns the response as a string. Call an LLM directly with the given prompt. Returns the response as a string.
Use this for classification, summarization, extraction, or any task where you Use this for classification, summarization, extraction, or any task where you
@ -1660,11 +1596,11 @@ interactions:
## Available Python Features ## Available Python Features
The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `sorted()`/`.sort(key=...)`, try/except, and the `json` module. The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `filter()`, `getattr()`, `sorted()`/`.sort(key=...)`, try/except, and the `json`, `re`, `math` modules.
Not supported: imports (other than `json`), class definitions, generators/yield, match statements, decorators, `with` statements. Not supported: most imports (only `json`, `re`, `math` are available), class definitions, generators/yield, match statements, decorators, `with` statements.
For pattern matching or text extraction, use the `regex_*` functions, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function. For pattern matching or text extraction, use `import re`, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function.
## Strategy Guide ## Strategy Guide
@ -1690,10 +1626,11 @@ interactions:
### Extracting data with regex ### Extracting data with regex
```python ```python
import re
numbers = [] numbers = []
results = await search("financial data", limit=20) results = await search("financial data", limit=20)
for r in results: for r in results:
amounts = await regex_findall(r'\$([\d,]+)', r['content']) amounts = re.findall(r'\$([\d,]+)', r['content'])
for a in amounts: for a in amounts:
numbers.append(int(a.replace(',', ''))) numbers.append(int(a.replace(',', '')))
if numbers: if numbers:
@ -1733,81 +1670,81 @@ interactions:
- content: What is the total revenue across all quarterly reports? - content: What is the total revenue across all quarterly reports?
role: user role: user
- content: null - content: null
reasoning: Need revenue from quarterly reports. Search for "quarterly report revenue". reasoning: Need to search for quarterly reports revenue.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor arguments: '{"code":"import re\n# search for revenue in quarterly reports\nresults = await search(\"quarterly
r in results[:5]:\n print(r[''document_title''], r[''score''], r[''content''][:200])"}' report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''], r[''score''])\n"}'
name: execute_code name: execute_code
id: call_no1egdsi id: call_exbbulxp
type: function type: function
- content: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''], - content: '{"code":"import re\n# search for revenue in quarterly reports\nresults = await search(\"quarterly report
r[''score''], r[''content''][:200])","stdout":"3\nQ1 Report 0.03226645663380623 Sales report Q1: Revenue was $100,000.\nQ2 revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''], r[''score''])\n","stdout":"3\nQ1
Report 0.03226645663380623 Sales report Q2: Revenue was $150,000.\nQ3 Report 0.032258063554763794 Sales report Q3: Report 0.03226645663380623\nQ2 Report 0.03226645663380623\nQ3 Report 0.032258063554763794\n","stderr":"","success":true}'
Revenue was $200,000.\n","stderr":"","success":true}'
role: tool role: tool
tool_call_id: call_no1egdsi tool_call_id: call_exbbulxp
- content: null - content: null
reasoning: Three reports with revenue numbers. Sum = 450k. Need citation chunks. Retrieve chunks. reasoning: We need revenue numbers. Let's fetch chunks.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"chunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''], arguments: '{"code":"# get chunks for each result\nchunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''],
chunk[''content''].strip())"}' chunk[''content''][:200])\n"}'
name: execute_code name: execute_code
id: call_sg5vtxpb id: call_2hd3mgon
type: function type: function
- content: '{"code":"chunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''], - content: '{"code":"# get chunks for each result\nchunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''],
chunk[''content''].strip())","stdout":"","stderr":"NameError: name ''results'' is not defined","success":false}' chunk[''content''][:200])\n","stdout":"","stderr":"NameError: name ''results'' is not defined","success":false}'
role: tool role: tool
tool_call_id: call_sg5vtxpb tool_call_id: call_2hd3mgon
- content: null - content: null
reasoning: Need to keep results variable. Use same scope. Let's re-run with storing results. reasoning: Need to re-run search inside same code.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n c arguments: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n chunk
= await get_chunk(r[''chunk_id''])\n chunks.append(c)\n print(c[''document_title''], c[''content''].strip())"}' = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''], chunk[''content''][:200])\n"}'
name: execute_code name: execute_code
id: call_h6pfbenb id: call_10n40kz9
type: function type: function
- content: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n c - content: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n chunk
= await get_chunk(r[''chunk_id''])\n chunks.append(c)\n print(c[''document_title''], c[''content''].strip())","stdout":"Q1 = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n print(chunk[''document_title''], chunk[''content''][:200])\n","stdout":"Q1
Report Sales report Q1: Revenue was $100,000.\nQ2 Report Sales report Q2: Revenue was $150,000.\nQ3 Report Sales Report Sales report Q1: Revenue was $100,000.\nQ2 Report Sales report Q2: Revenue was $150,000.\nQ3 Report Sales
report Q3: Revenue was $200,000.\n","stderr":"","success":true}' report Q3: Revenue was $200,000.\n","stderr":"","success":true}'
role: tool role: tool
tool_call_id: call_h6pfbenb tool_call_id: call_10n40kz9
- content: Now compute sum.
role: assistant
tool_calls:
- function:
arguments: '{"code":"total = 0\nfor c in chunks:\n nums = await regex_findall(r''\\$([\\d,]+)'', c[''content''])\n for
n in nums:\n total += int(n.replace('','', ''''))\nprint(total)"}'
name: execute_code
id: call_rlqh271l
type: function
- content: '{"code":"total = 0\nfor c in chunks:\n nums = await regex_findall(r''\\$([\\d,]+)'', c[''content''])\n for
n in nums:\n total += int(n.replace('','', ''''))\nprint(total)","stdout":"","stderr":"NameError: name ''chunks''
is not defined","success":false}'
role: tool
tool_call_id: call_rlqh271l
- content: null - content: null
reasoning: Variable scope lost. Let's combine. reasoning: Sum revenues.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n c arguments: '{"code":"total=0\nfor c in chunks:\n import re\n m=re.search(r''\\$([\\d,]+)'', c[''content''])\n if
= await get_chunk(r[''chunk_id''])\n chunks.append(c)\n\ntotal = 0\nfor c in chunks:\n nums = await regex_findall(r''\\$([\\d,]+)'', m:\n val=int(m.group(1).replace('','',''''))\n total+=val\nprint(total)\n"}'
c[''content''])\n for n in nums:\n total += int(n.replace('','', ''''))\nprint(total)"}'
name: execute_code name: execute_code
id: call_kbsx3dxm id: call_51jmnwfv
type: function type: function
- content: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n c - content: '{"code":"total=0\nfor c in chunks:\n import re\n m=re.search(r''\\$([\\d,]+)'', c[''content''])\n if
= await get_chunk(r[''chunk_id''])\n chunks.append(c)\n\ntotal = 0\nfor c in chunks:\n nums = await regex_findall(r''\\$([\\d,]+)'', m:\n val=int(m.group(1).replace('','',''''))\n total+=val\nprint(total)\n","stdout":"","stderr":"NameError:
c[''content''])\n for n in nums:\n total += int(n.replace('','', ''''))\nprint(total)","stdout":"450000\n","stderr":"","success":true}' name ''chunks'' is not defined","success":false}'
role: tool role: tool
tool_call_id: call_kbsx3dxm tool_call_id: call_51jmnwfv
- content: null
reasoning: Need to keep chunks variable. Let's combine.
role: assistant
tool_calls:
- function:
arguments: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n chunk
= await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n\ntotal=0\nimport re\nfor c in chunks:\n m=re.search(r''\\$([\\d,]+)'',
c[''content''])\n if m:\n val=int(m.group(1).replace('','',''''))\n total+=val\nprint(total)\n"}'
name: execute_code
id: call_axsiusi8
type: function
- content: '{"code":"results = await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n chunk
= await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n\ntotal=0\nimport re\nfor c in chunks:\n m=re.search(r''\\$([\\d,]+)'',
c[''content''])\n if m:\n val=int(m.group(1).replace('','',''''))\n total+=val\nprint(total)\n","stdout":"450000\n","stderr":"","success":true}'
role: tool
tool_call_id: call_axsiusi8
model: gpt-oss model: gpt-oss
reasoning_effort: low reasoning_effort: low
response_format: response_format:
@ -1830,6 +1767,7 @@ interactions:
strict: true strict: true
type: json_schema type: json_schema
stream: false stream: false
temperature: 0.0
tool_choice: auto tool_choice: auto
tools: tools:
- function: - function:
@ -1859,7 +1797,7 @@ interactions:
response: response:
headers: headers:
content-length: content-length:
- '880' - '980'
content-type: content-type:
- application/json - application/json
parsed_body: parsed_body:
@ -1867,21 +1805,22 @@ interactions:
- finish_reason: stop - finish_reason: stop
index: 0 index: 0
message: message:
content: '{"answer":"The total revenue across all quarterly reports is $450,000. This figure comes from three reports:\n- content: '{"answer":"The total revenue reported across all quarterly reports is $450,000. This figure is the sum
Q1 Report: $100,000\n- Q2 Report: $150,000\n- Q3 Report: $200,000\nSumming these gives the stated total.\n", "program":"results of $100,000 from Q1, $150,000 from Q2, and $200,000 from Q3, as extracted from the respective quarterly report
= await search(\"quarterly report revenue\", limit=20)\nchunks = []\nfor r in results:\n c = await get_chunk(r[''chunk_id''])\n chunks.append(c)\n\ntotal documents.","program":"import re\n# Search for quarterly report revenue chunks\nresults = await search(\"quarterly
= 0\nfor c in chunks:\n nums = await regex_findall(r''\\$([\\d,]+)'', c[''content''])\n for n in nums:\n total report revenue\", limit=20)\nchunks = []\nfor r in results:\n chunk = await get_chunk(r[''chunk_id''])\n chunks.append(chunk)\n#
+= int(n.replace('','', ''''))\nprint(total)"}' Sum revenue amounts\ntotal = 0\nfor c in chunks:\n m = re.search(r\"\\$([\\d,]+)\", c[''content''])\n if
m:\n val = int(m.group(1).replace('','', ''''))\n total += val\nprint(total)"}'
role: assistant role: assistant
created: 1772626970 created: 1773329189
id: chatcmpl-772 id: chatcmpl-169
model: gpt-oss model: gpt-oss
object: chat.completion object: chat.completion
system_fingerprint: fp_ollama system_fingerprint: fp_ollama
usage: usage:
completion_tokens: 178 completion_tokens: 186
prompt_tokens: 2744 prompt_tokens: 2655
total_tokens: 2922 total_tokens: 2841
status: status:
code: 200 code: 200
message: OK message: OK

87
tests/cassettes/test_rlm/TestClientRLMIntegration.test_rlm_count_documents.yaml
View file

@ -128,7 +128,7 @@ interactions:
connection: connection:
- keep-alive - keep-alive
content-length: content-length:
- '7721' - '7258'
content-type: content-type:
- application/json - application/json
host: host:
@ -173,18 +173,6 @@ interactions:
- `pictures`: list of figures/images with metadata - `pictures`: list of figures/images with metadata
- `pages`: page dimensions and metadata - `pages`: page dimensions and metadata
### await regex_findall(pattern, text) -> list[str]
Find all non-overlapping matches of a regular expression pattern in text.
### await regex_sub(pattern, repl, text) -> str
Replace all occurrences of a regular expression pattern with a replacement string.
### await regex_search(pattern, text) -> dict | None
Search for the first match of a pattern. Returns a dict with keys: group, groups, start, end — or None if no match.
### await regex_split(pattern, text) -> list[str]
Split text by a regular expression pattern.
### await llm(prompt) -> str ### await llm(prompt) -> str
Call an LLM directly with the given prompt. Returns the response as a string. Call an LLM directly with the given prompt. Returns the response as a string.
Use this for classification, summarization, extraction, or any task where you Use this for classification, summarization, extraction, or any task where you
@ -202,11 +190,11 @@ interactions:
## Available Python Features ## Available Python Features
The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `sorted()`/`.sort(key=...)`, try/except, and the `json` module. The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `filter()`, `getattr()`, `sorted()`/`.sort(key=...)`, try/except, and the `json`, `re`, `math` modules.
Not supported: imports (other than `json`), class definitions, generators/yield, match statements, decorators, `with` statements. Not supported: most imports (only `json`, `re`, `math` are available), class definitions, generators/yield, match statements, decorators, `with` statements.
For pattern matching or text extraction, use the `regex_*` functions, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function. For pattern matching or text extraction, use `import re`, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function.
## Strategy Guide ## Strategy Guide
@ -232,10 +220,11 @@ interactions:
### Extracting data with regex ### Extracting data with regex
```python ```python
import re
numbers = [] numbers = []
results = await search("financial data", limit=20) results = await search("financial data", limit=20)
for r in results: for r in results:
amounts = await regex_findall(r'\$([\d,]+)', r['content']) amounts = re.findall(r'\$([\d,]+)', r['content'])
for a in amounts: for a in amounts:
numbers.append(int(a.replace(',', ''))) numbers.append(int(a.replace(',', '')))
if numbers: if numbers:
@ -296,6 +285,7 @@ interactions:
strict: true strict: true
type: json_schema type: json_schema
stream: false stream: false
temperature: 0.0
tool_choice: auto tool_choice: auto
tools: tools:
- function: - function:
@ -325,7 +315,7 @@ interactions:
response: response:
headers: headers:
content-length: content-length:
- '522' - '525'
content-type: content-type:
- application/json - application/json
parsed_body: parsed_body:
@ -338,20 +328,20 @@ interactions:
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"docs = await list_documents(limit=1000)\nprint(len(docs))"}' arguments: '{"code":"docs = await list_documents(limit=1000)\nprint(len(docs))\n"}'
name: execute_code name: execute_code
id: call_cthflnpr id: call_04viywlj
index: 0 index: 0
type: function type: function
created: 1772626945 created: 1773329125
id: chatcmpl-979 id: chatcmpl-653
model: gpt-oss model: gpt-oss
object: chat.completion object: chat.completion
system_fingerprint: fp_ollama system_fingerprint: fp_ollama
usage: usage:
completion_tokens: 45 completion_tokens: 47
prompt_tokens: 1686 prompt_tokens: 1592
total_tokens: 1731 total_tokens: 1639
status: status:
code: 200 code: 200
message: OK message: OK
@ -364,7 +354,7 @@ interactions:
connection: connection:
- keep-alive - keep-alive
content-length: content-length:
- '8163' - '7706'
content-type: content-type:
- application/json - application/json
host: host:
@ -409,18 +399,6 @@ interactions:
- `pictures`: list of figures/images with metadata - `pictures`: list of figures/images with metadata
- `pages`: page dimensions and metadata - `pages`: page dimensions and metadata
### await regex_findall(pattern, text) -> list[str]
Find all non-overlapping matches of a regular expression pattern in text.
### await regex_sub(pattern, repl, text) -> str
Replace all occurrences of a regular expression pattern with a replacement string.
### await regex_search(pattern, text) -> dict | None
Search for the first match of a pattern. Returns a dict with keys: group, groups, start, end — or None if no match.
### await regex_split(pattern, text) -> list[str]
Split text by a regular expression pattern.
### await llm(prompt) -> str ### await llm(prompt) -> str
Call an LLM directly with the given prompt. Returns the response as a string. Call an LLM directly with the given prompt. Returns the response as a string.
Use this for classification, summarization, extraction, or any task where you Use this for classification, summarization, extraction, or any task where you
@ -438,11 +416,11 @@ interactions:
## Available Python Features ## Available Python Features
The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `sorted()`/`.sort(key=...)`, try/except, and the `json` module. The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `filter()`, `getattr()`, `sorted()`/`.sort(key=...)`, try/except, and the `json`, `re`, `math` modules.
Not supported: imports (other than `json`), class definitions, generators/yield, match statements, decorators, `with` statements. Not supported: most imports (only `json`, `re`, `math` are available), class definitions, generators/yield, match statements, decorators, `with` statements.
For pattern matching or text extraction, use the `regex_*` functions, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function. For pattern matching or text extraction, use `import re`, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function.
## Strategy Guide ## Strategy Guide
@ -468,10 +446,11 @@ interactions:
### Extracting data with regex ### Extracting data with regex
```python ```python
import re
numbers = [] numbers = []
results = await search("financial data", limit=20) results = await search("financial data", limit=20)
for r in results: for r in results:
amounts = await regex_findall(r'\$([\d,]+)', r['content']) amounts = re.findall(r'\$([\d,]+)', r['content'])
for a in amounts: for a in amounts:
numbers.append(int(a.replace(',', ''))) numbers.append(int(a.replace(',', '')))
if numbers: if numbers:
@ -515,13 +494,13 @@ interactions:
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"docs = await list_documents(limit=1000)\nprint(len(docs))"}' arguments: '{"code":"docs = await list_documents(limit=1000)\nprint(len(docs))\n"}'
name: execute_code name: execute_code
id: call_cthflnpr id: call_04viywlj
type: function type: function
- content: '{"code":"docs = await list_documents(limit=1000)\nprint(len(docs))","stdout":"3\n","stderr":"","success":true}' - content: '{"code":"docs = await list_documents(limit=1000)\nprint(len(docs))\n","stdout":"3\n","stderr":"","success":true}'
role: tool role: tool
tool_call_id: call_cthflnpr tool_call_id: call_04viywlj
model: gpt-oss model: gpt-oss
reasoning_effort: low reasoning_effort: low
response_format: response_format:
@ -544,6 +523,7 @@ interactions:
strict: true strict: true
type: json_schema type: json_schema
stream: false stream: false
temperature: 0.0
tool_choice: auto tool_choice: auto
tools: tools:
- function: - function:
@ -573,7 +553,7 @@ interactions:
response: response:
headers: headers:
content-length: content-length:
- '459' - '416'
content-type: content-type:
- application/json - application/json
parsed_body: parsed_body:
@ -581,18 +561,17 @@ interactions:
- finish_reason: stop - finish_reason: stop
index: 0 index: 0
message: message:
content: '{"answer":"There are 3 documents in the database.","program":"docs = await list_documents(limit=1000)\nprint(f''There content: '{"answer":"There are 3 documents in the database.","program":"docs = await list_documents(limit=1000)\nprint(len(docs))"}'
are {len(docs)} documents in the database.'')" }'
role: assistant role: assistant
created: 1772626947 created: 1773329134
id: chatcmpl-490 id: chatcmpl-151
model: gpt-oss model: gpt-oss
object: chat.completion object: chat.completion
system_fingerprint: fp_ollama system_fingerprint: fp_ollama
usage: usage:
completion_tokens: 49 completion_tokens: 38
prompt_tokens: 1773 prompt_tokens: 1683
total_tokens: 1822 total_tokens: 1721
status: status:
code: 200 code: 200
message: OK message: OK

2618
tests/cassettes/test_rlm/TestClientRLMIntegration.test_rlm_search_and_extract.yaml
View file

File diff suppressed because one or more lines are too long

407
tests/cassettes/test_rlm/TestClientRLMIntegration.test_rlm_search_and_get_chunk.yaml
View file

File diff suppressed because one or more lines are too long

1771
tests/cassettes/test_rlm/TestClientRLMIntegration.test_rlm_semantic_analysis_with_llm.yaml
View file

File diff suppressed because one or more lines are too long

94
tests/cassettes/test_rlm/TestClientRLMIntegration.test_rlm_with_filter.yaml
View file

@ -128,7 +128,7 @@ interactions:
connection: connection:
- keep-alive - keep-alive
content-length: content-length:
- '7715' - '7252'
content-type: content-type:
- application/json - application/json
host: host:
@ -173,18 +173,6 @@ interactions:
- `pictures`: list of figures/images with metadata - `pictures`: list of figures/images with metadata
- `pages`: page dimensions and metadata - `pages`: page dimensions and metadata
### await regex_findall(pattern, text) -> list[str]
Find all non-overlapping matches of a regular expression pattern in text.
### await regex_sub(pattern, repl, text) -> str
Replace all occurrences of a regular expression pattern with a replacement string.
### await regex_search(pattern, text) -> dict | None
Search for the first match of a pattern. Returns a dict with keys: group, groups, start, end — or None if no match.
### await regex_split(pattern, text) -> list[str]
Split text by a regular expression pattern.
### await llm(prompt) -> str ### await llm(prompt) -> str
Call an LLM directly with the given prompt. Returns the response as a string. Call an LLM directly with the given prompt. Returns the response as a string.
Use this for classification, summarization, extraction, or any task where you Use this for classification, summarization, extraction, or any task where you
@ -202,11 +190,11 @@ interactions:
## Available Python Features ## Available Python Features
The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `sorted()`/`.sort(key=...)`, try/except, and the `json` module. The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `filter()`, `getattr()`, `sorted()`/`.sort(key=...)`, try/except, and the `json`, `re`, `math` modules.
Not supported: imports (other than `json`), class definitions, generators/yield, match statements, decorators, `with` statements. Not supported: most imports (only `json`, `re`, `math` are available), class definitions, generators/yield, match statements, decorators, `with` statements.
For pattern matching or text extraction, use the `regex_*` functions, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function. For pattern matching or text extraction, use `import re`, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function.
## Strategy Guide ## Strategy Guide
@ -232,10 +220,11 @@ interactions:
### Extracting data with regex ### Extracting data with regex
```python ```python
import re
numbers = [] numbers = []
results = await search("financial data", limit=20) results = await search("financial data", limit=20)
for r in results: for r in results:
amounts = await regex_findall(r'\$([\d,]+)', r['content']) amounts = re.findall(r'\$([\d,]+)', r['content'])
for a in amounts: for a in amounts:
numbers.append(int(a.replace(',', ''))) numbers.append(int(a.replace(',', '')))
if numbers: if numbers:
@ -296,6 +285,7 @@ interactions:
strict: true strict: true
type: json_schema type: json_schema
stream: false stream: false
temperature: 0.0
tool_choice: auto tool_choice: auto
tools: tools:
- function: - function:
@ -325,7 +315,7 @@ interactions:
response: response:
headers: headers:
content-length: content-length:
- '522' - '576'
content-type: content-type:
- application/json - application/json
parsed_body: parsed_body:
@ -334,24 +324,25 @@ interactions:
index: 0 index: 0
message: message:
content: '' content: ''
reasoning: Need to list documents. reasoning: We need to list documents.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"docs = await list_documents(limit=1000)\nprint(len(docs))\n"}' arguments: '{"code":"docs = await list_documents(limit=1000)\nprint(len(docs))\nfor d in docs:\n print(d[''id''],
d.get(''title''))"}'
name: execute_code name: execute_code
id: call_jsd3hga7 id: call_nap68rkx
index: 0 index: 0
type: function type: function
created: 1772626976 created: 1773329124
id: chatcmpl-987 id: chatcmpl-461
model: gpt-oss model: gpt-oss
object: chat.completion object: chat.completion
system_fingerprint: fp_ollama system_fingerprint: fp_ollama
usage: usage:
completion_tokens: 46 completion_tokens: 64
prompt_tokens: 1684 prompt_tokens: 1590
total_tokens: 1730 total_tokens: 1654
status: status:
code: 200 code: 200
message: OK message: OK
@ -364,7 +355,7 @@ interactions:
connection: connection:
- keep-alive - keep-alive
content-length: content-length:
- '8160' - '7846'
content-type: content-type:
- application/json - application/json
host: host:
@ -409,18 +400,6 @@ interactions:
- `pictures`: list of figures/images with metadata - `pictures`: list of figures/images with metadata
- `pages`: page dimensions and metadata - `pages`: page dimensions and metadata
### await regex_findall(pattern, text) -> list[str]
Find all non-overlapping matches of a regular expression pattern in text.
### await regex_sub(pattern, repl, text) -> str
Replace all occurrences of a regular expression pattern with a replacement string.
### await regex_search(pattern, text) -> dict | None
Search for the first match of a pattern. Returns a dict with keys: group, groups, start, end — or None if no match.
### await regex_split(pattern, text) -> list[str]
Split text by a regular expression pattern.
### await llm(prompt) -> str ### await llm(prompt) -> str
Call an LLM directly with the given prompt. Returns the response as a string. Call an LLM directly with the given prompt. Returns the response as a string.
Use this for classification, summarization, extraction, or any task where you Use this for classification, summarization, extraction, or any task where you
@ -438,11 +417,11 @@ interactions:
## Available Python Features ## Available Python Features
The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `sorted()`/`.sort(key=...)`, try/except, and the `json` module. The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, async/await, `map()`, `filter()`, `getattr()`, `sorted()`/`.sort(key=...)`, try/except, and the `json`, `re`, `math` modules.
Not supported: imports (other than `json`), class definitions, generators/yield, match statements, decorators, `with` statements. Not supported: most imports (only `json`, `re`, `math` are available), class definitions, generators/yield, match statements, decorators, `with` statements.
For pattern matching or text extraction, use the `regex_*` functions, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function. For pattern matching or text extraction, use `import re`, string methods (`str.split`, `str.find`, `str.startswith`, `in` operator), or the `llm()` function.
## Strategy Guide ## Strategy Guide
@ -468,10 +447,11 @@ interactions:
### Extracting data with regex ### Extracting data with regex
```python ```python
import re
numbers = [] numbers = []
results = await search("financial data", limit=20) results = await search("financial data", limit=20)
for r in results: for r in results:
amounts = await regex_findall(r'\$([\d,]+)', r['content']) amounts = re.findall(r'\$([\d,]+)', r['content'])
for a in amounts: for a in amounts:
numbers.append(int(a.replace(',', ''))) numbers.append(int(a.replace(',', '')))
if numbers: if numbers:
@ -511,17 +491,19 @@ interactions:
- content: How many documents are available? - content: How many documents are available?
role: user role: user
- content: null - content: null
reasoning: Need to list documents. reasoning: We need to list documents.
role: assistant role: assistant
tool_calls: tool_calls:
- function: - function:
arguments: '{"code":"docs = await list_documents(limit=1000)\nprint(len(docs))\n"}' arguments: '{"code":"docs = await list_documents(limit=1000)\nprint(len(docs))\nfor d in docs:\n print(d[''id''],
d.get(''title''))"}'
name: execute_code name: execute_code
id: call_jsd3hga7 id: call_nap68rkx
type: function type: function
- content: '{"code":"docs = await list_documents(limit=1000)\nprint(len(docs))\n","stdout":"1\n","stderr":"","success":true}' - content: '{"code":"docs = await list_documents(limit=1000)\nprint(len(docs))\nfor d in docs:\n print(d[''id''],
d.get(''title''))","stdout":"1\n7b1434a1-bbe5-4ae1-bb3e-5400eed94d72 Cats\n","stderr":"","success":true}'
role: tool role: tool
tool_call_id: call_jsd3hga7 tool_call_id: call_nap68rkx
model: gpt-oss model: gpt-oss
reasoning_effort: low reasoning_effort: low
response_format: response_format:
@ -544,6 +526,7 @@ interactions:
strict: true strict: true
type: json_schema type: json_schema
stream: false stream: false
temperature: 0.0
tool_choice: auto tool_choice: auto
tools: tools:
- function: - function:
@ -573,7 +556,7 @@ interactions:
response: response:
headers: headers:
content-length: content-length:
- '430' - '484'
content-type: content-type:
- application/json - application/json
parsed_body: parsed_body:
@ -581,17 +564,18 @@ interactions:
- finish_reason: stop - finish_reason: stop
index: 0 index: 0
message: message:
content: '{"answer":"There is 1 document available in the knowledge base.","program":"docs = await list_documents(limit=1000)\nprint(len(docs))"}' content: '{"answer":"There is 1 document available in the knowledge base.","program":"docs = await list_documents(limit=1000)\nprint(len(docs))\nfor
d in docs:\n print(d[''id''], d.get(''title''))"}'
role: assistant role: assistant
created: 1772626977 created: 1773329133
id: chatcmpl-959 id: chatcmpl-985
model: gpt-oss model: gpt-oss
object: chat.completion object: chat.completion
system_fingerprint: fp_ollama system_fingerprint: fp_ollama
usage: usage:
completion_tokens: 37 completion_tokens: 59
prompt_tokens: 1774 prompt_tokens: 1741
total_tokens: 1811 total_tokens: 1800
status: status:
code: 200 code: 200
message: OK message: OK

1801
tests/cassettes/test_rlm/TestClientRLMIntegration.test_rlm_with_preloaded_documents.yaml
View file

File diff suppressed because it is too large Load diff

78
uv.lock
View file

@ -1529,7 +1529,7 @@ requires-dist = [
{ name = "pydantic-ai-slim", extras = ["openai", "fastmcp", "logfire", "ag-ui"], specifier = ">=1.66.0" }, { name = "pydantic-ai-slim", extras = ["openai", "fastmcp", "logfire", "ag-ui"], specifier = ">=1.66.0" },
{ name = "pydantic-ai-slim", extras = ["vertexai"], marker = "extra == 'vertexai'" }, { name = "pydantic-ai-slim", extras = ["vertexai"], marker = "extra == 'vertexai'" },
{ name = "pydantic-ai-slim", extras = ["voyageai"], marker = "extra == 'voyageai'" }, { name = "pydantic-ai-slim", extras = ["voyageai"], marker = "extra == 'voyageai'" },
{ name = "pydantic-monty", specifier = ">=0.0.7" }, { name = "pydantic-monty", specifier = ">=0.0.8" },
{ name = "python-dotenv", specifier = ">=1.2.2" }, { name = "python-dotenv", specifier = ">=1.2.2" },
{ name = "pyyaml", specifier = ">=6.0.3" }, { name = "pyyaml", specifier = ">=6.0.3" },
{ name = "rich", specifier = ">=14.3.3" }, { name = "rich", specifier = ">=14.3.3" },
@ -3790,46 +3790,46 @@ wheels = [
[[package]] [[package]]
name = "pydantic-monty" name = "pydantic-monty"
version = "0.0.7" version = "0.0.8"
source = { registry = "https://pypi.org/simple" } source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/f5/e3/0d8b2b025628477c839f894e632f5197872b19df0a86b2ec30fac3b5960a/pydantic_monty-0.0.7.tar.gz", hash = "sha256:2189ea1d7aadab2f95374733d692f51d1206379a4fc7ce18ab46895512e88f92", size = 684705, upload-time = "2026-02-19T14:12:47.235Z" } sdist = { url = "https://files.pythonhosted.org/packages/47/bf/e9794b562c207406d8fda0cf4fea810943a5e8a85fe69e5505046179df16/pydantic_monty-0.0.8.tar.gz", hash = "sha256:8135e781a184f971825c1d2eb6d621598103e900f6e0d34291ff0bf35df6142f", size = 802646, upload-time = "2026-03-10T14:46:51.353Z" }
wheels = [ wheels = [
{ url = "https://files.pythonhosted.org/packages/ce/7e/ca0884108c3237bb15bb2a1b3f24ddd957b9c750f1ed3211801497941999/pydantic_monty-0.0.7-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:f35e18f284524d26d5f27084e2b93eb40139055bbf0cab6221a043eb5e9ce2dc", size = 6264252, upload-time = "2026-02-19T14:13:59.317Z" }, { url = "https://files.pythonhosted.org/packages/f4/4f/7d7c7531be850469bccfbbf3cfede9e95d92b1d8e7b245d9dc77a599d6e4/pydantic_monty-0.0.8-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:025b380c0ed728bdf88e3ed60d5977498d4bb9da61cd81d9cabdaecce16f5755", size = 6699454, upload-time = "2026-03-10T14:46:39.422Z" },
{ url = "https://files.pythonhosted.org/packages/5a/5b/31f70c7792a857bacbdce90b8aae4629c31a9fec35f0116d91a2fb53241b/pydantic_monty-0.0.7-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:8e5d8924c65bb1ced60785a156e28c73f7f79f164b4f090dc26312c3917ffff7", size = 6133285, upload-time = "2026-02-19T14:14:46.577Z" }, { url = "https://files.pythonhosted.org/packages/c0/35/074daa5fd92e4a5c1e49c8fae06036e194139feef9a51b4db82d0fee7e54/pydantic_monty-0.0.8-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:76846d77ebda3414beb8c9e5da9eaef722e06606dc0307613186d888e775dc51", size = 6743273, upload-time = "2026-03-10T14:46:16.184Z" },
{ url = "https://files.pythonhosted.org/packages/42/56/c92216c0427e8a10a01fa98f29252f6fabd8ca80ca193e0fd30fe28e65c1/pydantic_monty-0.0.7-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6279a468469d5a3b80d94dd0ab6110cd291a1dfbb057fa7d6dbad1f499be855d", size = 6059856, upload-time = "2026-02-19T14:13:02.594Z" }, { url = "https://files.pythonhosted.org/packages/55/0d/e6cb1e9e1c2e51501d8f7848c18803780164948e338350ab94769690f207/pydantic_monty-0.0.8-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3b58149d6a8998ffed80f626c10bf0de7e65964aae1dfad80db8ecb00968fb1a", size = 6503552, upload-time = "2026-03-10T14:45:26.083Z" },
{ url = "https://files.pythonhosted.org/packages/b5/a7/bc3e67b12d8a9da65f2677d9a48bc1e055a1d853d48572ba4845a64075cf/pydantic_monty-0.0.7-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:cb5feb69a5902d059db5dab269f90423b85a22163668422be47ccac8d7f7c44a", size = 6313780, upload-time = "2026-02-19T14:13:46.45Z" }, { url = "https://files.pythonhosted.org/packages/5f/a9/286f7eb6c95d7877f6f8b9bcbe26e2d988fa142cd77509e48e67302478bf/pydantic_monty-0.0.8-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:1b99bb030ff8e95b160c11702b9a6823705b7dcc1a49a2c1dccc43c2538bfe27", size = 6765377, upload-time = "2026-03-10T14:45:14.472Z" },
{ url = "https://files.pythonhosted.org/packages/c8/97/a9b856b17ee1e54892dafbb7ea29305520cae2dcd8aafe82a26a0edbc33c/pydantic_monty-0.0.7-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a2f1913e9729aa6711092ecbfce764df199a4787fe3e23a7ed74c78bf846579e", size = 6856827, upload-time = "2026-02-19T14:13:40.836Z" }, { url = "https://files.pythonhosted.org/packages/74/76/85268f6305bc5b153be7c0860e69ce3b9ba916daa4a419f53d8a777e9a39/pydantic_monty-0.0.8-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b05b17fc2b8875e0efea047416fc0cd28a8018c040b25387454996b98540ccfc", size = 7324571, upload-time = "2026-03-10T14:45:48.786Z" },
{ url = "https://files.pythonhosted.org/packages/98/57/2d8184b9f5a0b2b3bb47fdad7061c6a182699824efe6de9d8dd19ee68c0a/pydantic_monty-0.0.7-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ec528f9f4194e6298757ad99e25da47f06f49ae2bc176ee26f49da5eb1dd7849", size = 6870737, upload-time = "2026-02-19T14:13:53.602Z" }, { url = "https://files.pythonhosted.org/packages/11/6a/2855c6149f6ba3138c7bfb009c07d528e2df12802e3216928b1289bbf233/pydantic_monty-0.0.8-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:97fa5deef4d8cdcf60a4d8a4e7a34099deae1ad4b33acc1c33ac2e1cc348a1c2", size = 7533828, upload-time = "2026-03-10T14:46:55.386Z" },
{ url = "https://files.pythonhosted.org/packages/6b/b3/fe3d3eff82b41e517739841a492d7a48ea2daf8e7b822299b848b5d4c0aa/pydantic_monty-0.0.7-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75405b9186a9acfa49cd66aa339b5a2450d733a2d59fae20cc8be45e45204d5f", size = 6611843, upload-time = "2026-02-19T14:13:49.957Z" }, { url = "https://files.pythonhosted.org/packages/31/63/44b5bb5798323f7f735f5855a0d3f478d6852d9d1774427d77e31b5dbffb/pydantic_monty-0.0.8-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f1aabd56af5db51c4af512142fe7ffc866b6a20dcd039a4aad5245ef42768f21", size = 7271978, upload-time = "2026-03-10T14:45:33.903Z" },
{ url = "https://files.pythonhosted.org/packages/ff/d2/fdd8fe135ea14e30b40adadc896dda6c805596688998c9bcdfd8d85a16cf/pydantic_monty-0.0.7-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:1917e42fce4733f92f5f6ad64ae4d0e87abbf9fb284ef52589ac3e292e928bfe", size = 6692856, upload-time = "2026-02-19T14:13:00.635Z" }, { url = "https://files.pythonhosted.org/packages/4b/68/ce82eb571e45afbe3c0b9544fe3ebf93f841ec895fea0d39c9604a0a421f/pydantic_monty-0.0.8-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:9782e58da29176a3fb0ce8ec808571d0be99c1e2ad167637225246e594e85f13", size = 7187140, upload-time = "2026-03-10T14:46:41.784Z" },
{ url = "https://files.pythonhosted.org/packages/0d/a6/fdde6f8d76aa0cff4b53060b63d7f09dbb19da61a967cb4b3dfd972acf1c/pydantic_monty-0.0.7-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:d72a5d4f3ee7f9d2630b0379e4cfb397e181eb0b16e8c49a03f80ba6471edb89", size = 6236587, upload-time = "2026-02-19T14:14:32.602Z" }, { url = "https://files.pythonhosted.org/packages/5b/45/778bc260195ddb892f284c3cb8ab8cbcb0542e6a18f11b7e50a592b507ba/pydantic_monty-0.0.8-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:ff7fb7ff3f4e830ef9b28a76e634219195b552c0dfed3471fb4910708db56221", size = 6677996, upload-time = "2026-03-10T14:46:03.163Z" },
{ url = "https://files.pythonhosted.org/packages/1b/7e/0580bbc001a39252b2f7da4b7504ac10572e4ca0ec967aebc5a9d752b6f7/pydantic_monty-0.0.7-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:20028220981516912f130986354ef6c926b98778146ca349560cb852e44d9ca6", size = 6672260, upload-time = "2026-02-19T14:13:26.527Z" }, { url = "https://files.pythonhosted.org/packages/1e/02/8e8396b83d19ec70a09c24b0245177a595c2b7d6d092c6f6c7d3310b191c/pydantic_monty-0.0.8-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:ce7222d923676900827e3951e65f854d65f50b65ed8c7a84011d3472773d51bf", size = 7136513, upload-time = "2026-03-10T14:45:52.179Z" },
{ url = "https://files.pythonhosted.org/packages/d8/53/578a7b781a5714db5c4b1989c6e876d30caa0adf8a5a4caad89abc306667/pydantic_monty-0.0.7-cp312-cp312-win32.whl", hash = "sha256:e28b1c3ed52892f8ac12ee0f2b535402dfe1cb1e5c18128f1cb69eb8b66c285a", size = 6131085, upload-time = "2026-02-19T14:14:13.296Z" }, { url = "https://files.pythonhosted.org/packages/fd/24/53d06af74b82043be9c4960c38bbc255eeb3de9f2a4d450f942912630bb3/pydantic_monty-0.0.8-cp312-cp312-win32.whl", hash = "sha256:4cb59e1e7b1a3d573247a871a87c88506ce9fb68bbd7648598e171cf2f04747e", size = 6582168, upload-time = "2026-03-10T14:45:58.197Z" },
{ url = "https://files.pythonhosted.org/packages/56/98/20bd45fcd472937b1b3438b7587e209e3cfd447c30d02f654b86b44adaad/pydantic_monty-0.0.7-cp312-cp312-win_amd64.whl", hash = "sha256:031dfab63ff9d7acdc641852e0d822603038cef1c27c5060900b9fd51cc853d0", size = 6664431, upload-time = "2026-02-19T14:13:29.968Z" }, { url = "https://files.pythonhosted.org/packages/25/0f/55a16faf379139263ad852421734cb096390777d299ef7f185ec10404656/pydantic_monty-0.0.8-cp312-cp312-win_amd64.whl", hash = "sha256:45bf11e3b795cc470a91cbd7cfeb9d96f7a60387e8da146a11bf952b4371aba7", size = 7335422, upload-time = "2026-03-10T14:45:28.301Z" },
{ url = "https://files.pythonhosted.org/packages/ec/fe/d8cb6c30d9d7bcc7d3c8d2c349a227e2a83cd1fbe7182f4941896eb35443/pydantic_monty-0.0.7-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:55d36818f8e35872ed35e395b41df8acc460bcdbbfd471fe0c39e293a1d50db5", size = 6262596, upload-time = "2026-02-19T14:14:15.2Z" }, { url = "https://files.pythonhosted.org/packages/27/46/3268001a639052515d5a55ea2f1e087ae1e5f7aa9d7bc62c4808d731fff1/pydantic_monty-0.0.8-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:f303f1d979213dcb365c69de3912daa70a32af019bb5ee86e086f584638974f2", size = 6698529, upload-time = "2026-03-10T14:45:39.712Z" },
{ url = "https://files.pythonhosted.org/packages/81/7a/f6b4881ca9779bd87eb8d8c0823133b56c232cf09d765c07a7f91d641490/pydantic_monty-0.0.7-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:acb437458d93d54a9658656545fb6c9b396dbe66f68633b3c57bfd2f4aa1d400", size = 6133793, upload-time = "2026-02-19T14:14:06.498Z" }, { url = "https://files.pythonhosted.org/packages/f4/22/28d6b7f8f7a1e0881c449310a6f2c8ee0cf85dc4434ae0f7e633dfcf5bcf/pydantic_monty-0.0.8-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:b8cc698da6f7f11743df7c48b959eea000e8e30511c7e1318b67543e25985062", size = 6743849, upload-time = "2026-03-10T14:46:48.023Z" },
{ url = "https://files.pythonhosted.org/packages/39/b9/dfcffd95ff233b8c98db9254242d9c10190989762016d18509aa04d43b1b/pydantic_monty-0.0.7-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b196345ffa1997041cb870ea693148feafe270575e2c2963532eedde0e84dedf", size = 6059400, upload-time = "2026-02-19T14:13:38.953Z" }, { url = "https://files.pythonhosted.org/packages/7b/ab/e3dfe057af472e4065297d69aea0cf30616d01366a29e02d0a2739f22b93/pydantic_monty-0.0.8-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:90f6da093164e99012b49b39ba1e64c166ccd126128d114f9e2c66df6fb695c4", size = 6503266, upload-time = "2026-03-10T14:46:19.594Z" },
{ url = "https://files.pythonhosted.org/packages/6b/2e/d6ecef842024267ddf4128613342b8985a7444e74f3a4a312713c913a91a/pydantic_monty-0.0.7-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d471e3cfe77d62edaf43b7f0962b95270ee4243abea12cb8e8cf1ad972dc3612", size = 6312625, upload-time = "2026-02-19T14:13:36.901Z" }, { url = "https://files.pythonhosted.org/packages/0a/82/d3e9aa9bd9ac69b3584216166a189e11370913ffcbd2a57a5cac6ce2d4ba/pydantic_monty-0.0.8-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:f2432ef62140554f5970991b7df41e064824741a807515658f91283c75669086", size = 6765032, upload-time = "2026-03-10T14:45:20.571Z" },
{ url = "https://files.pythonhosted.org/packages/75/2e/e4a2a9fbc3640bcee15b80c2f8ba0f97bf989c58c01d6da187524f71d12b/pydantic_monty-0.0.7-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3a67771afd385579bf3f894ce933fb9e467fba9a632ccf27246e271d448f6f5f", size = 6859902, upload-time = "2026-02-19T14:14:26.67Z" }, { url = "https://files.pythonhosted.org/packages/f8/9d/7ab11be8eff998bf9283c7bf444254cff5212f87fe3f2a9a2f7436cce6d7/pydantic_monty-0.0.8-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:99951afb4d722212c2ce85c303b5e87d50756adaff46817ad0e60e95eb1e5141", size = 7324673, upload-time = "2026-03-10T14:45:37.957Z" },
{ url = "https://files.pythonhosted.org/packages/d2/4a/7aaf5c793f52e3403892a2de1f5dd18ae38234d82111cc9b7d92443e5b0d/pydantic_monty-0.0.7-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:bf662e1bbee4ddd318d5b8bfa9233173045029be0f67f15f816955b246bb7ec0", size = 6870524, upload-time = "2026-02-19T14:13:28.208Z" }, { url = "https://files.pythonhosted.org/packages/39/a0/7f026ece228cc990e58aa27f2ce5af26d042baaa0186cb451f3e04ff0abe/pydantic_monty-0.0.8-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:bdef70921b408378f9bc38bce4952d3c176b3f7833aa782068b310390901c516", size = 7533774, upload-time = "2026-03-10T14:46:24.265Z" },
{ url = "https://files.pythonhosted.org/packages/c3/a9/c16f078864a273460923f1371b769c2719e1ce1ad86bc9031e3ed7fb3eae/pydantic_monty-0.0.7-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0151ff59a8a0d9e29ddb448affa33943108121e6e324795646a2f5facaf1a5d8", size = 6611960, upload-time = "2026-02-19T14:14:38.812Z" }, { url = "https://files.pythonhosted.org/packages/07/e7/72f250ffd005520ad8cdffb387241a9dd92fc70bcbdd769720918bd34495/pydantic_monty-0.0.8-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:00b5dee7bef619e7661f77bef765f483605bcd2a79c6b8bf5c910afa1c93fc40", size = 7272179, upload-time = "2026-03-10T14:45:08.085Z" },
{ url = "https://files.pythonhosted.org/packages/20/d3/b3ef3432558a8cc9551d8b80a028a0f51cd2a518275932e03359eac3dc39/pydantic_monty-0.0.7-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:45f17a65134d3a0031e1f54d143770699f6a0ce92a1e74f0ae4914e52370f058", size = 6691834, upload-time = "2026-02-19T14:13:34.661Z" }, { url = "https://files.pythonhosted.org/packages/b8/7c/97c87c2a315ba4376bfb83197586365003005e01d6547df7f6d77b80d13f/pydantic_monty-0.0.8-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:5f4c6f6fb2ebae0bc80520af71e1057055413ca96fd33f13f3c612a085e50fb8", size = 7186684, upload-time = "2026-03-10T14:46:49.833Z" },
{ url = "https://files.pythonhosted.org/packages/ef/56/1ab5d1cbc0edfb522f0c28c9f5a7fc74eea6355234f73833087524d034bf/pydantic_monty-0.0.7-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:ede6e68cb8a1f7216e26b0b2fb6cd0eae7a92104be8a49d1042e9e428de9262b", size = 6235704, upload-time = "2026-02-19T14:13:48.276Z" }, { url = "https://files.pythonhosted.org/packages/09/42/2eea55906fee8bef7c1024bf2d35e2c301b15b562934731bdae25db448cb/pydantic_monty-0.0.8-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:3ab3c558a648942d4d31e7f668d60d2a2e129751a3e8e9dc27b1e6d635e9e627", size = 6677272, upload-time = "2026-03-10T14:45:54.037Z" },
{ url = "https://files.pythonhosted.org/packages/c4/d1/cdebae67b0543f696ed7daff8587dc8a458e6552b52d5877cb8e55be74b4/pydantic_monty-0.0.7-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:4b2fd51eea05a0cc37bb91f326efdb1acbcd4b8262dac1c55aeb208e51254978", size = 6671530, upload-time = "2026-02-19T14:12:56.96Z" }, { url = "https://files.pythonhosted.org/packages/40/0a/066e53d4693b680e39080d3af4f234c1ff9976f7621b8a49dd2a41710431/pydantic_monty-0.0.8-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:782d686d217b537e6fa9047aa3444d67b3b7cc69bf6faf34078c992ceaeb1e9e", size = 7136493, upload-time = "2026-03-10T14:45:30.014Z" },
{ url = "https://files.pythonhosted.org/packages/9f/53/c0dacaec260b71050fd6b31d09570f9d74bbb2a2e9586032694e92b9fa59/pydantic_monty-0.0.7-cp313-cp313-win32.whl", hash = "sha256:40f2092970c5899ac2a2784d712a4c7e194b33cd0133315254e4baf141cd6c93", size = 6130341, upload-time = "2026-02-19T14:14:09.701Z" }, { url = "https://files.pythonhosted.org/packages/81/c1/46dc300f87314aef883a57ae5a35ba45a463c09f64d3d9c9f0b620672734/pydantic_monty-0.0.8-cp313-cp313-win32.whl", hash = "sha256:ef0db454757cb92974890b11c7b0969d8c0d95944c821f6fc6cd23846d1d2aa4", size = 6581014, upload-time = "2026-03-10T14:46:07.886Z" },
{ url = "https://files.pythonhosted.org/packages/3e/05/31490a7a899d8bbb2e513630ea6f591ceb8a111c91fe7573a96c9f6b6327/pydantic_monty-0.0.7-cp313-cp313-win_amd64.whl", hash = "sha256:42cee2646415bb9bd7da428d169783203618a418f960c6f75c7a74d6946d6b31", size = 6664341, upload-time = "2026-02-19T14:14:19.008Z" }, { url = "https://files.pythonhosted.org/packages/b0/2a/cf156df19a1612ca5ddcbd982645e54c5485e83215d9532cc9aff791f854/pydantic_monty-0.0.8-cp313-cp313-win_amd64.whl", hash = "sha256:dbf8c7cfaff2b345f8c1bfba98fdc282e790fef5c601f37c8d5355ccd45073de", size = 7335041, upload-time = "2026-03-10T14:46:21.371Z" },
{ url = "https://files.pythonhosted.org/packages/99/15/64aff358df0b822dd22f212fec501e3944edffe978a4ab05530ea641dc68/pydantic_monty-0.0.7-cp314-cp314-macosx_10_12_x86_64.whl", hash = "sha256:c97b2e1dcd0126417892595c1da724a8c4348f7dcec26ba774117bd51bde46f8", size = 6266090, upload-time = "2026-02-19T14:13:12.364Z" }, { url = "https://files.pythonhosted.org/packages/a5/69/5bedc7ad67fdd9e4f04007477f5c414b54c51d47c5dfdd7abad4c78663aa/pydantic_monty-0.0.8-cp314-cp314-macosx_10_12_x86_64.whl", hash = "sha256:47990770ed74af1e8e2160a7dd925aa1e4fd1bf4ae9658ffd1cdc32eb5c8c6e8", size = 6700454, upload-time = "2026-03-10T14:45:56.247Z" },
{ url = "https://files.pythonhosted.org/packages/64/90/7b5a4292eb9993eb8be9d958b5a57764818eeda471e3e79be7da4e9b49ba/pydantic_monty-0.0.7-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:6f40e6e133b309ba733874f5980ab6cf867ec8cea2a6a389a641819cd8dcb7cd", size = 6152219, upload-time = "2026-02-19T14:13:20.734Z" }, { url = "https://files.pythonhosted.org/packages/bf/35/06aaa9c766a83e7e95219bfb6cb88bd0a87803f85eb3f596b82da0cb3009/pydantic_monty-0.0.8-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:9534f6236b3ebdd09f0f7d71e508e68736733d24cdda2a6c0a758914261c75e5", size = 6760180, upload-time = "2026-03-10T14:45:22.982Z" },
{ url = "https://files.pythonhosted.org/packages/43/e4/2740af0157eb3c6f10c16b0d8376b8c9cf0b910720fe90229885bccb4a91/pydantic_monty-0.0.7-cp314-cp314-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:57f2a327b6aa7402a2b2c3ddb3964bd45f12597f8f950dd4c5905b843b353b73", size = 6060942, upload-time = "2026-02-19T14:12:45.601Z" }, { url = "https://files.pythonhosted.org/packages/f3/b8/eaa4a4f0b3a1c343773317027bb5d1e11a1b0c1ad01d3f0921a7f547d346/pydantic_monty-0.0.8-cp314-cp314-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:76c4ffd8275d520628732d82e7410e5f1f69ef5af274d676f1f2f9221fd85a34", size = 6504414, upload-time = "2026-03-10T14:45:12.984Z" },
{ url = "https://files.pythonhosted.org/packages/f6/26/1cf235c2cc8e219a94ed8b11151280ba89e8020a475b6280c89e62f7275f/pydantic_monty-0.0.7-cp314-cp314-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:771f1f158af0de2480ea2a8862e4c0c7f79e9a13cc3e17529002e1abfc077f95", size = 6315477, upload-time = "2026-02-19T14:14:11.314Z" }, { url = "https://files.pythonhosted.org/packages/9d/79/dbb0875ad2b565d7ef1981feda4438ab743130f4031107aaadc9212488dd/pydantic_monty-0.0.8-cp314-cp314-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:badaa22749fa7a22ee2cb88f6deb48fc191cb2f41237dd630593259ed9f30b67", size = 6766768, upload-time = "2026-03-10T14:46:29.12Z" },
{ url = "https://files.pythonhosted.org/packages/b8/41/0faca7b9d8868822b7177ae941f193f397479bb114d3a6396466167a3198/pydantic_monty-0.0.7-cp314-cp314-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a4182312ee8c26d8834e76375b2b5c766cb5d86d1dcf1515aa95e02704fcad83", size = 6862130, upload-time = "2026-02-19T14:13:22.375Z" }, { url = "https://files.pythonhosted.org/packages/25/cb/bd6bef8fa2cfe807dd5ef36ab8ce6d094ecdad0050cf57dec4c8a438d413/pydantic_monty-0.0.8-cp314-cp314-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e39104684eda1ae3c290e3a4369bef9d00f9b637be8515802bc1523fecb5160d", size = 7326073, upload-time = "2026-03-10T14:45:50.679Z" },
{ url = "https://files.pythonhosted.org/packages/34/7b/0f2bd4105a285f50f17af721e83a76ebc1186a9f07a2a29d6d576490a232/pydantic_monty-0.0.7-cp314-cp314-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8751696fe66fb1bdd429d98fde3a7f4b7dce9cb45f22095e28b96b690a422a2c", size = 6872292, upload-time = "2026-02-19T14:14:08.078Z" }, { url = "https://files.pythonhosted.org/packages/aa/44/b64b6e2857519d5fdc66f74998019e585e5c3bf2cf8deb7b77419d29db2a/pydantic_monty-0.0.8-cp314-cp314-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8c2e5b3b11b794f82504bb6929f4101f0db84933986aee9b46ce7561add152e9", size = 7535251, upload-time = "2026-03-10T14:46:04.645Z" },
{ url = "https://files.pythonhosted.org/packages/c9/18/4380820d62d348afb1355814ea674788e28db7a73108a486e0b8898987de/pydantic_monty-0.0.7-cp314-cp314-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:40b73cd1137bb4fd9bf95ed5f87e48d960f7d556c30eeafde6996f908abbf183", size = 6636567, upload-time = "2026-02-19T14:14:01.464Z" }, { url = "https://files.pythonhosted.org/packages/da/11/4e1524d94e33427990cffd74eaf94a023724c872f11d42ac90eebd74ccc0/pydantic_monty-0.0.8-cp314-cp314-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a94fc87b2a9b1b66a09f35b819b1c7e7da7702b21c923cdca21fa13129486b45", size = 7288739, upload-time = "2026-03-10T14:45:35.609Z" },
{ url = "https://files.pythonhosted.org/packages/3e/57/29e5f89a558a6409d514bb2790c72442ec65804cbf1df6a870bbc0038673/pydantic_monty-0.0.7-cp314-cp314-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:c1fa45a66757de5ea45c0809e15643bc2521959dbe2bc231694b22fa189decc9", size = 6693896, upload-time = "2026-02-19T14:14:34.128Z" }, { url = "https://files.pythonhosted.org/packages/2c/7d/7e667c72c9742a6725b04d21faf50e8f552a0e23da9ca1cbeba891961c9a/pydantic_monty-0.0.8-cp314-cp314-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:70b7479e7bd47d274fbd6278a625289e71b1a4aad400f40c7a4a89fe9a50952c", size = 7189195, upload-time = "2026-03-10T14:46:09.399Z" },
{ url = "https://files.pythonhosted.org/packages/f6/26/5886d0f57ddb5ddf766ee2d0a4b3032267be9efd49a7c95c4d87a0b4b6a9/pydantic_monty-0.0.7-cp314-cp314-musllinux_1_1_aarch64.whl", hash = "sha256:ffe8122db9f0f64619a66f4cee2f577245ba59158b7d651a2eae08df691d34f9", size = 6236867, upload-time = "2026-02-19T14:14:20.704Z" }, { url = "https://files.pythonhosted.org/packages/7b/3f/3243277e2c6bf4c3e4684fbc78c316a8965dbbb012b573b38978d8628bfc/pydantic_monty-0.0.8-cp314-cp314-musllinux_1_1_aarch64.whl", hash = "sha256:48b8c9cb9a96a5f28b03669771368a444c8b50c758b6a5bd0d148fa02db3f65b", size = 6679333, upload-time = "2026-03-10T14:45:24.494Z" },
{ url = "https://files.pythonhosted.org/packages/b5/72/1bb8741baf84f217d92291b862f8a8cb64d735fe4be20be2827fdf787593/pydantic_monty-0.0.7-cp314-cp314-musllinux_1_1_x86_64.whl", hash = "sha256:2122a5b6df53843329af01f6671300747449608d9cdf88ae5f9cf9977794e7a2", size = 6673504, upload-time = "2026-02-19T14:14:24.517Z" }, { url = "https://files.pythonhosted.org/packages/0c/51/88152b89f5288e9d3cd28e71f79a6567421e20d8f00b0514b7819a29a8bb/pydantic_monty-0.0.8-cp314-cp314-musllinux_1_1_x86_64.whl", hash = "sha256:b005f10798a1b58a12b5643f69a7b54208bd4965d16ca2bd21d13fca4d1a4f67", size = 7137771, upload-time = "2026-03-10T14:46:33.043Z" },
{ url = "https://files.pythonhosted.org/packages/d1/14/a4ff2bfe46350ffde4b5edc1f293b252cff90063f1f4cece49affe5a6462/pydantic_monty-0.0.7-cp314-cp314-win32.whl", hash = "sha256:bfbea2eddb9eef186326a6dfb27d79f8de434d7a3979f36f03b04216234a0275", size = 6131872, upload-time = "2026-02-19T14:13:14.437Z" }, { url = "https://files.pythonhosted.org/packages/d8/38/baf5a66ed72b931de7ce92251822d6ffb752582389ff4f4c853742cee029/pydantic_monty-0.0.8-cp314-cp314-win32.whl", hash = "sha256:b143bba29c274e15424a097af6ae85a1e81e6c2fb7184ee7a93fbf10997dbbd3", size = 6584038, upload-time = "2026-03-10T14:46:34.53Z" },
{ url = "https://files.pythonhosted.org/packages/60/1f/d873f280aae5cbd27021189843fbd5f77be4262a7654ef30445d984518ab/pydantic_monty-0.0.7-cp314-cp314-win_amd64.whl", hash = "sha256:1b750afceef78f5c5d3e3e3c32a8060b3a7e1b97e3a00ac2bede5bc5e87cde8f", size = 6687125, upload-time = "2026-02-19T14:13:04.317Z" }, { url = "https://files.pythonhosted.org/packages/71/80/bfda690914fa15c68f8be9e824e62c4054118a9a72304735221446a89014/pydantic_monty-0.0.8-cp314-cp314-win_amd64.whl", hash = "sha256:f4bc9185bb5f37f3220a978889b4bc6f822a41ee4d5523c17eef4d869aca66e8", size = 7351170, upload-time = "2026-03-10T14:46:57.025Z" },
] ]
[[package]] [[package]]