2693 lines
159 KiB
YAML
2693 lines
159 KiB
YAML
interactions:
|
|
- request:
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '108'
|
|
content-type:
|
|
- application/json
|
|
host:
|
|
- localhost:11434
|
|
method: POST
|
|
parsed_body:
|
|
encoding_format: base64
|
|
input:
|
|
- 'Sales report Q1: Revenue was $100,000.'
|
|
model: qwen3-embedding:4b
|
|
uri: http://localhost:11434/v1/embeddings
|
|
response:
|
|
headers:
|
|
content-type:
|
|
- application/json
|
|
transfer-encoding:
|
|
- chunked
|
|
parsed_body:
|
|
data:
|
|
- embedding: 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
|
|
index: 0
|
|
object: embedding
|
|
model: qwen3-embedding:4b
|
|
object: list
|
|
usage:
|
|
prompt_tokens: 17
|
|
total_tokens: 17
|
|
status:
|
|
code: 200
|
|
message: OK
|
|
- request:
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '108'
|
|
content-type:
|
|
- application/json
|
|
host:
|
|
- localhost:11434
|
|
method: POST
|
|
parsed_body:
|
|
encoding_format: base64
|
|
input:
|
|
- 'Sales report Q2: Revenue was $150,000.'
|
|
model: qwen3-embedding:4b
|
|
uri: http://localhost:11434/v1/embeddings
|
|
response:
|
|
headers:
|
|
content-type:
|
|
- application/json
|
|
transfer-encoding:
|
|
- chunked
|
|
parsed_body:
|
|
data:
|
|
- embedding: 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
|
|
index: 0
|
|
object: embedding
|
|
model: qwen3-embedding:4b
|
|
object: list
|
|
usage:
|
|
prompt_tokens: 17
|
|
total_tokens: 17
|
|
status:
|
|
code: 200
|
|
message: OK
|
|
- request:
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '108'
|
|
content-type:
|
|
- application/json
|
|
host:
|
|
- localhost:11434
|
|
method: POST
|
|
parsed_body:
|
|
encoding_format: base64
|
|
input:
|
|
- 'Sales report Q3: Revenue was $200,000.'
|
|
model: qwen3-embedding:4b
|
|
uri: http://localhost:11434/v1/embeddings
|
|
response:
|
|
headers:
|
|
content-type:
|
|
- application/json
|
|
transfer-encoding:
|
|
- chunked
|
|
parsed_body:
|
|
data:
|
|
- embedding: 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
|
|
index: 0
|
|
object: embedding
|
|
model: qwen3-embedding:4b
|
|
object: list
|
|
usage:
|
|
prompt_tokens: 17
|
|
total_tokens: 17
|
|
status:
|
|
code: 200
|
|
message: OK
|
|
- request:
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '7790'
|
|
content-type:
|
|
- application/json
|
|
host:
|
|
- localhost:11434
|
|
method: POST
|
|
parsed_body:
|
|
messages:
|
|
- content: |-
|
|
You are a Recursive Language Model (RLM) agent that solves complex research questions by writing and executing Python code.
|
|
|
|
IMPORTANT: You MUST use the `execute_code` tool to run Python code. The functions described below are ONLY available inside the execute_code tool - you cannot access them any other way. Always execute code to answer questions; do not just describe what code would do.
|
|
|
|
CRITICAL: Inside execute_code, these functions are ALREADY available in the namespace. Do NOT import them - just use them directly:
|
|
- search("query") ✓ CORRECT
|
|
- from haiku.rag import search ✗ WRONG - will fail
|
|
|
|
You have access to a sandboxed Python environment with these haiku.rag functions (use them directly, no imports needed):
|
|
|
|
## Available Functions
|
|
|
|
### search(query, limit=10) -> list[dict]
|
|
Search the knowledge base using hybrid search (vector + full-text).
|
|
Returns list of dicts with keys: chunk_id, content, document_id, document_title, document_uri, score, page_numbers, headings
|
|
|
|
### list_documents(limit=10, offset=0) -> list[dict]
|
|
List available documents in the knowledge base.
|
|
Returns list of dicts with keys: id, title, uri, created_at
|
|
|
|
### get_document(id_or_title) -> str | None
|
|
Get the full text content of a document by ID, title, or URI.
|
|
Returns the document content as a string, or None if not found.
|
|
|
|
### get_docling_document(id_or_title) -> DoclingDocument | None
|
|
Get the structured DoclingDocument object for advanced analysis.
|
|
Returns a DoclingDocument object, or None if not found.
|
|
See "DoclingDocument API" section below for how to use it.
|
|
|
|
### llm(prompt) -> str
|
|
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
|
|
already have the content and just need LLM reasoning.
|
|
|
|
## Pre-loaded Documents Variable
|
|
|
|
If documents were pre-loaded for this session, a `documents` variable is available:
|
|
```python
|
|
# documents is a list of dicts with keys: id, title, uri, content
|
|
for doc in documents:
|
|
print(doc['title'], len(doc['content']))
|
|
```
|
|
Check if it exists with: `if 'documents' in dir(): ...`
|
|
|
|
## Standard Library Modules
|
|
You can import any Python standard library module.
|
|
|
|
## Strategy Guide
|
|
|
|
1. **Explore First**: Start by listing documents or searching to understand what's available. Document names may differ from filenames (e.g., "tbmed593.pdf" might be stored as "TB MED 593" or similar).
|
|
2. **If get_document returns None**: Use `list_documents()` to see actual document titles, or `search()` to find relevant content.
|
|
3. **Iterative Refinement**: Run code, examine results, adjust your approach based on what you find.
|
|
4. **Use print() Liberally**: The REPL captures stdout - print intermediate results to see what you're working with.
|
|
5. **Aggregate with Code**: For counting, averaging, or comparing across documents, write loops and use collections.
|
|
6. **Use llm() for Classification/Extraction**: When you need to classify, summarize, or extract structured data from content you already have, use llm().
|
|
7. **Cite Your Sources**: Track which documents/chunks informed your answer for citation.
|
|
|
|
## DoclingDocument API
|
|
|
|
When you call `get_docling_document(id_or_title)`, you get a DoclingDocument object for structured document analysis.
|
|
|
|
### Properties
|
|
- `doc.texts` - List of all text items (paragraphs, headings, etc.)
|
|
- `doc.tables` - List of all tables
|
|
- `doc.pictures` - List of all pictures/figures
|
|
- `doc.name` - Document name
|
|
|
|
### Methods
|
|
- `doc.iterate_items(with_groups=False)` - Iterate all items with hierarchy level
|
|
Returns tuples of (item, level) where level is nesting depth
|
|
- `doc.export_to_markdown()` - Export entire document as markdown string
|
|
|
|
### Text Item Properties
|
|
- `item.text` - The text content
|
|
- `item.label` - Type: title, paragraph, section_header, list_item, etc. (lowercase enum values)
|
|
- `item.prov` - Provenance (page numbers, bounding boxes)
|
|
|
|
### Table Access
|
|
- `table.data.num_rows`, `table.data.num_cols` - Dimensions
|
|
- `table.data.table_cells` - List of TableCell objects
|
|
- `cell.text`, `cell.start_row_offset_idx`, `cell.start_col_offset_idx`
|
|
|
|
### Example Usage
|
|
```python
|
|
doc = get_docling_document("My Document")
|
|
|
|
# Get all headings
|
|
headings = [t.text for t in doc.texts if "header" in str(t.label)]
|
|
|
|
# Iterate with structure
|
|
for item, level in doc.iterate_items():
|
|
print(" " * level + item.text[:50])
|
|
|
|
# Extract table data
|
|
for table in doc.tables:
|
|
for cell in table.data.table_cells:
|
|
print(f"Row {cell.start_row_offset_idx}, Col {cell.start_col_offset_idx}: {cell.text}")
|
|
```
|
|
|
|
## Example Patterns
|
|
|
|
### Counting documents matching a condition
|
|
```python
|
|
docs = list_documents(limit=100)
|
|
count = 0
|
|
for doc in docs:
|
|
content = get_document(doc['id'])
|
|
if content and 'keyword' in content.lower():
|
|
count += 1
|
|
print(f"Found in: {doc['title']}")
|
|
print(f"Total: {count}")
|
|
```
|
|
|
|
### Aggregating data across documents
|
|
```python
|
|
import re
|
|
numbers = []
|
|
results = search("financial data", limit=20)
|
|
for r in results:
|
|
matches = re.findall(r'\$([\d,]+)', r['content'])
|
|
for m in matches:
|
|
numbers.append(int(m.replace(',', '')))
|
|
print(f"Average: ${sum(numbers)/len(numbers):,.2f}")
|
|
```
|
|
|
|
### Using llm() for classification
|
|
```python
|
|
# Get document content
|
|
content = get_document("Q1 Report")
|
|
# Use llm() to classify sentiment
|
|
sentiment = llm(f"Classify the sentiment as positive, negative, or mixed: {content}")
|
|
print(sentiment)
|
|
```
|
|
|
|
## Workflow
|
|
|
|
1. **ALWAYS start by using execute_code** to explore the knowledge base
|
|
2. Run multiple code blocks as needed to gather information
|
|
3. After collecting data, provide your final answer
|
|
|
|
## Output Format
|
|
|
|
CRITICAL: Your final response MUST be valid JSON matching this exact schema:
|
|
```json
|
|
{"answer": "Your complete answer here as a string", "program": "Your final consolidated program here as a string"}
|
|
```
|
|
|
|
- `answer`: A clear answer to the user's question with key findings and references to specific documents/chunks.
|
|
- `program`: A single, self-contained Python program that produces the answer. Consolidate your exploratory code executions into one clean script.
|
|
|
|
Do NOT return arbitrary JSON structures. Always use the exact format: {"answer": "...", "program": "..."}
|
|
|
|
CRITICAL: You MUST call execute_code at least once before providing your answer. Never give up without trying to execute code first.
|
|
role: system
|
|
- content: What is the total revenue across all quarterly reports?
|
|
role: user
|
|
model: gpt-oss
|
|
reasoning_effort: low
|
|
stream: false
|
|
tool_choice: auto
|
|
tools:
|
|
- function:
|
|
description: |-
|
|
<summary>Execute Python code in a Docker-sandboxed environment.
|
|
|
|
The code has access to haiku.rag functions (search, list_documents,
|
|
get_document, get_docling_document, llm) and any Python standard
|
|
library module.
|
|
|
|
Use print() to output results.</summary>
|
|
<returns>
|
|
<description>Structured result with success status, stdout, and stderr.</description>
|
|
</returns>
|
|
name: execute_code
|
|
parameters:
|
|
additionalProperties: false
|
|
properties:
|
|
code:
|
|
description: Python code to execute.
|
|
type: string
|
|
required:
|
|
- code
|
|
type: object
|
|
strict: true
|
|
type: function
|
|
- function:
|
|
description: Result from RLM agent execution.
|
|
name: final_result
|
|
parameters:
|
|
additionalProperties: false
|
|
properties:
|
|
answer:
|
|
description: The answer to the user's question
|
|
type: string
|
|
program:
|
|
description: The final consolidated program
|
|
type: string
|
|
required:
|
|
- answer
|
|
- program
|
|
type: object
|
|
strict: true
|
|
type: function
|
|
uri: http://localhost:11434/v1/chat/completions
|
|
response:
|
|
headers:
|
|
content-length:
|
|
- '777'
|
|
content-type:
|
|
- application/json
|
|
parsed_body:
|
|
choices:
|
|
- finish_reason: tool_calls
|
|
index: 0
|
|
message:
|
|
content: ''
|
|
reasoning: Need to find quarterly reports, extract revenue amounts, sum. Likely documents titled like "Q1 Report",
|
|
"Q2 Report"... Let's search "quarterly report revenue".
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"results = search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in
|
|
results[:5]:\n print(r[''document_title''], r[''page_numbers''], r[''score''])\n"}'
|
|
name: execute_code
|
|
id: call_arzz3ioj
|
|
index: 0
|
|
type: function
|
|
created: 1770373346
|
|
id: chatcmpl-682
|
|
model: gpt-oss
|
|
object: chat.completion
|
|
system_fingerprint: fp_ollama
|
|
usage:
|
|
completion_tokens: 106
|
|
prompt_tokens: 1749
|
|
total_tokens: 1855
|
|
status:
|
|
code: 200
|
|
message: OK
|
|
- request:
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '8709'
|
|
content-type:
|
|
- application/json
|
|
host:
|
|
- localhost:11434
|
|
method: POST
|
|
parsed_body:
|
|
messages:
|
|
- content: |-
|
|
You are a Recursive Language Model (RLM) agent that solves complex research questions by writing and executing Python code.
|
|
|
|
IMPORTANT: You MUST use the `execute_code` tool to run Python code. The functions described below are ONLY available inside the execute_code tool - you cannot access them any other way. Always execute code to answer questions; do not just describe what code would do.
|
|
|
|
CRITICAL: Inside execute_code, these functions are ALREADY available in the namespace. Do NOT import them - just use them directly:
|
|
- search("query") ✓ CORRECT
|
|
- from haiku.rag import search ✗ WRONG - will fail
|
|
|
|
You have access to a sandboxed Python environment with these haiku.rag functions (use them directly, no imports needed):
|
|
|
|
## Available Functions
|
|
|
|
### search(query, limit=10) -> list[dict]
|
|
Search the knowledge base using hybrid search (vector + full-text).
|
|
Returns list of dicts with keys: chunk_id, content, document_id, document_title, document_uri, score, page_numbers, headings
|
|
|
|
### list_documents(limit=10, offset=0) -> list[dict]
|
|
List available documents in the knowledge base.
|
|
Returns list of dicts with keys: id, title, uri, created_at
|
|
|
|
### get_document(id_or_title) -> str | None
|
|
Get the full text content of a document by ID, title, or URI.
|
|
Returns the document content as a string, or None if not found.
|
|
|
|
### get_docling_document(id_or_title) -> DoclingDocument | None
|
|
Get the structured DoclingDocument object for advanced analysis.
|
|
Returns a DoclingDocument object, or None if not found.
|
|
See "DoclingDocument API" section below for how to use it.
|
|
|
|
### llm(prompt) -> str
|
|
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
|
|
already have the content and just need LLM reasoning.
|
|
|
|
## Pre-loaded Documents Variable
|
|
|
|
If documents were pre-loaded for this session, a `documents` variable is available:
|
|
```python
|
|
# documents is a list of dicts with keys: id, title, uri, content
|
|
for doc in documents:
|
|
print(doc['title'], len(doc['content']))
|
|
```
|
|
Check if it exists with: `if 'documents' in dir(): ...`
|
|
|
|
## Standard Library Modules
|
|
You can import any Python standard library module.
|
|
|
|
## Strategy Guide
|
|
|
|
1. **Explore First**: Start by listing documents or searching to understand what's available. Document names may differ from filenames (e.g., "tbmed593.pdf" might be stored as "TB MED 593" or similar).
|
|
2. **If get_document returns None**: Use `list_documents()` to see actual document titles, or `search()` to find relevant content.
|
|
3. **Iterative Refinement**: Run code, examine results, adjust your approach based on what you find.
|
|
4. **Use print() Liberally**: The REPL captures stdout - print intermediate results to see what you're working with.
|
|
5. **Aggregate with Code**: For counting, averaging, or comparing across documents, write loops and use collections.
|
|
6. **Use llm() for Classification/Extraction**: When you need to classify, summarize, or extract structured data from content you already have, use llm().
|
|
7. **Cite Your Sources**: Track which documents/chunks informed your answer for citation.
|
|
|
|
## DoclingDocument API
|
|
|
|
When you call `get_docling_document(id_or_title)`, you get a DoclingDocument object for structured document analysis.
|
|
|
|
### Properties
|
|
- `doc.texts` - List of all text items (paragraphs, headings, etc.)
|
|
- `doc.tables` - List of all tables
|
|
- `doc.pictures` - List of all pictures/figures
|
|
- `doc.name` - Document name
|
|
|
|
### Methods
|
|
- `doc.iterate_items(with_groups=False)` - Iterate all items with hierarchy level
|
|
Returns tuples of (item, level) where level is nesting depth
|
|
- `doc.export_to_markdown()` - Export entire document as markdown string
|
|
|
|
### Text Item Properties
|
|
- `item.text` - The text content
|
|
- `item.label` - Type: title, paragraph, section_header, list_item, etc. (lowercase enum values)
|
|
- `item.prov` - Provenance (page numbers, bounding boxes)
|
|
|
|
### Table Access
|
|
- `table.data.num_rows`, `table.data.num_cols` - Dimensions
|
|
- `table.data.table_cells` - List of TableCell objects
|
|
- `cell.text`, `cell.start_row_offset_idx`, `cell.start_col_offset_idx`
|
|
|
|
### Example Usage
|
|
```python
|
|
doc = get_docling_document("My Document")
|
|
|
|
# Get all headings
|
|
headings = [t.text for t in doc.texts if "header" in str(t.label)]
|
|
|
|
# Iterate with structure
|
|
for item, level in doc.iterate_items():
|
|
print(" " * level + item.text[:50])
|
|
|
|
# Extract table data
|
|
for table in doc.tables:
|
|
for cell in table.data.table_cells:
|
|
print(f"Row {cell.start_row_offset_idx}, Col {cell.start_col_offset_idx}: {cell.text}")
|
|
```
|
|
|
|
## Example Patterns
|
|
|
|
### Counting documents matching a condition
|
|
```python
|
|
docs = list_documents(limit=100)
|
|
count = 0
|
|
for doc in docs:
|
|
content = get_document(doc['id'])
|
|
if content and 'keyword' in content.lower():
|
|
count += 1
|
|
print(f"Found in: {doc['title']}")
|
|
print(f"Total: {count}")
|
|
```
|
|
|
|
### Aggregating data across documents
|
|
```python
|
|
import re
|
|
numbers = []
|
|
results = search("financial data", limit=20)
|
|
for r in results:
|
|
matches = re.findall(r'\$([\d,]+)', r['content'])
|
|
for m in matches:
|
|
numbers.append(int(m.replace(',', '')))
|
|
print(f"Average: ${sum(numbers)/len(numbers):,.2f}")
|
|
```
|
|
|
|
### Using llm() for classification
|
|
```python
|
|
# Get document content
|
|
content = get_document("Q1 Report")
|
|
# Use llm() to classify sentiment
|
|
sentiment = llm(f"Classify the sentiment as positive, negative, or mixed: {content}")
|
|
print(sentiment)
|
|
```
|
|
|
|
## Workflow
|
|
|
|
1. **ALWAYS start by using execute_code** to explore the knowledge base
|
|
2. Run multiple code blocks as needed to gather information
|
|
3. After collecting data, provide your final answer
|
|
|
|
## Output Format
|
|
|
|
CRITICAL: Your final response MUST be valid JSON matching this exact schema:
|
|
```json
|
|
{"answer": "Your complete answer here as a string", "program": "Your final consolidated program here as a string"}
|
|
```
|
|
|
|
- `answer`: A clear answer to the user's question with key findings and references to specific documents/chunks.
|
|
- `program`: A single, self-contained Python program that produces the answer. Consolidate your exploratory code executions into one clean script.
|
|
|
|
Do NOT return arbitrary JSON structures. Always use the exact format: {"answer": "...", "program": "..."}
|
|
|
|
CRITICAL: You MUST call execute_code at least once before providing your answer. Never give up without trying to execute code first.
|
|
role: system
|
|
- content: What is the total revenue across all quarterly reports?
|
|
role: user
|
|
- content: |-
|
|
<think>
|
|
Need to find quarterly reports, extract revenue amounts, sum. Likely documents titled like "Q1 Report", "Q2 Report"... Let's search "quarterly report revenue".
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"results = search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''],
|
|
r[''page_numbers''], r[''score''])\n"}'
|
|
name: execute_code
|
|
id: call_arzz3ioj
|
|
type: function
|
|
- content: '{"code":"results = search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''],
|
|
r[''page_numbers''], r[''score''])\n","stdout":"3\nQ1 Report [] 0.03226645663380623\nQ2 Report [] 0.03226645663380623\nQ3
|
|
Report [] 0.032258063554763794\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_arzz3ioj
|
|
model: gpt-oss
|
|
reasoning_effort: low
|
|
stream: false
|
|
tool_choice: auto
|
|
tools:
|
|
- function:
|
|
description: |-
|
|
<summary>Execute Python code in a Docker-sandboxed environment.
|
|
|
|
The code has access to haiku.rag functions (search, list_documents,
|
|
get_document, get_docling_document, llm) and any Python standard
|
|
library module.
|
|
|
|
Use print() to output results.</summary>
|
|
<returns>
|
|
<description>Structured result with success status, stdout, and stderr.</description>
|
|
</returns>
|
|
name: execute_code
|
|
parameters:
|
|
additionalProperties: false
|
|
properties:
|
|
code:
|
|
description: Python code to execute.
|
|
type: string
|
|
required:
|
|
- code
|
|
type: object
|
|
strict: true
|
|
type: function
|
|
- function:
|
|
description: Result from RLM agent execution.
|
|
name: final_result
|
|
parameters:
|
|
additionalProperties: false
|
|
properties:
|
|
answer:
|
|
description: The answer to the user's question
|
|
type: string
|
|
program:
|
|
description: The final consolidated program
|
|
type: string
|
|
required:
|
|
- answer
|
|
- program
|
|
type: object
|
|
strict: true
|
|
type: function
|
|
uri: http://localhost:11434/v1/chat/completions
|
|
response:
|
|
headers:
|
|
content-length:
|
|
- '1307'
|
|
content-type:
|
|
- application/json
|
|
parsed_body:
|
|
choices:
|
|
- finish_reason: tool_calls
|
|
index: 0
|
|
message:
|
|
content: ''
|
|
reasoning: We have 3 reports. Need to extract revenue. Let's fetch each document content and find revenue. Use regex
|
|
for "$...".
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"import re\nreports = [''Q1 Report'', ''Q2 Report'', ''Q3 Report'']\nrevenues = {}\nfor
|
|
rep in reports:\n content = get_document(rep)\n if content is None:\n # try by title\n for
|
|
doc in list_documents():\n if rep.lower() in doc[''title''].lower():\n content =
|
|
get_document(doc[''id''])\n break\n if content:\n # find patterns like \"Revenue:
|
|
$1,234,567\"\n matches = re.findall(r''Revenue[:\\s]*\\$([\\d,]+)'', content)\n amounts = [int(m.replace('','',''''))
|
|
for m in matches]\n if amounts:\n revenues[rep] = sum(amounts)\n else:\n revenues[rep]
|
|
= None\n else:\n revenues[rep] = None\nprint(revenues)\n"}'
|
|
name: execute_code
|
|
id: call_vuqzymvs
|
|
index: 0
|
|
type: function
|
|
created: 1770373351
|
|
id: chatcmpl-118
|
|
model: gpt-oss
|
|
object: chat.completion
|
|
system_fingerprint: fp_ollama
|
|
usage:
|
|
completion_tokens: 245
|
|
prompt_tokens: 1975
|
|
total_tokens: 2220
|
|
status:
|
|
code: 200
|
|
message: OK
|
|
- request:
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '10684'
|
|
content-type:
|
|
- application/json
|
|
host:
|
|
- localhost:11434
|
|
method: POST
|
|
parsed_body:
|
|
messages:
|
|
- content: |-
|
|
You are a Recursive Language Model (RLM) agent that solves complex research questions by writing and executing Python code.
|
|
|
|
IMPORTANT: You MUST use the `execute_code` tool to run Python code. The functions described below are ONLY available inside the execute_code tool - you cannot access them any other way. Always execute code to answer questions; do not just describe what code would do.
|
|
|
|
CRITICAL: Inside execute_code, these functions are ALREADY available in the namespace. Do NOT import them - just use them directly:
|
|
- search("query") ✓ CORRECT
|
|
- from haiku.rag import search ✗ WRONG - will fail
|
|
|
|
You have access to a sandboxed Python environment with these haiku.rag functions (use them directly, no imports needed):
|
|
|
|
## Available Functions
|
|
|
|
### search(query, limit=10) -> list[dict]
|
|
Search the knowledge base using hybrid search (vector + full-text).
|
|
Returns list of dicts with keys: chunk_id, content, document_id, document_title, document_uri, score, page_numbers, headings
|
|
|
|
### list_documents(limit=10, offset=0) -> list[dict]
|
|
List available documents in the knowledge base.
|
|
Returns list of dicts with keys: id, title, uri, created_at
|
|
|
|
### get_document(id_or_title) -> str | None
|
|
Get the full text content of a document by ID, title, or URI.
|
|
Returns the document content as a string, or None if not found.
|
|
|
|
### get_docling_document(id_or_title) -> DoclingDocument | None
|
|
Get the structured DoclingDocument object for advanced analysis.
|
|
Returns a DoclingDocument object, or None if not found.
|
|
See "DoclingDocument API" section below for how to use it.
|
|
|
|
### llm(prompt) -> str
|
|
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
|
|
already have the content and just need LLM reasoning.
|
|
|
|
## Pre-loaded Documents Variable
|
|
|
|
If documents were pre-loaded for this session, a `documents` variable is available:
|
|
```python
|
|
# documents is a list of dicts with keys: id, title, uri, content
|
|
for doc in documents:
|
|
print(doc['title'], len(doc['content']))
|
|
```
|
|
Check if it exists with: `if 'documents' in dir(): ...`
|
|
|
|
## Standard Library Modules
|
|
You can import any Python standard library module.
|
|
|
|
## Strategy Guide
|
|
|
|
1. **Explore First**: Start by listing documents or searching to understand what's available. Document names may differ from filenames (e.g., "tbmed593.pdf" might be stored as "TB MED 593" or similar).
|
|
2. **If get_document returns None**: Use `list_documents()` to see actual document titles, or `search()` to find relevant content.
|
|
3. **Iterative Refinement**: Run code, examine results, adjust your approach based on what you find.
|
|
4. **Use print() Liberally**: The REPL captures stdout - print intermediate results to see what you're working with.
|
|
5. **Aggregate with Code**: For counting, averaging, or comparing across documents, write loops and use collections.
|
|
6. **Use llm() for Classification/Extraction**: When you need to classify, summarize, or extract structured data from content you already have, use llm().
|
|
7. **Cite Your Sources**: Track which documents/chunks informed your answer for citation.
|
|
|
|
## DoclingDocument API
|
|
|
|
When you call `get_docling_document(id_or_title)`, you get a DoclingDocument object for structured document analysis.
|
|
|
|
### Properties
|
|
- `doc.texts` - List of all text items (paragraphs, headings, etc.)
|
|
- `doc.tables` - List of all tables
|
|
- `doc.pictures` - List of all pictures/figures
|
|
- `doc.name` - Document name
|
|
|
|
### Methods
|
|
- `doc.iterate_items(with_groups=False)` - Iterate all items with hierarchy level
|
|
Returns tuples of (item, level) where level is nesting depth
|
|
- `doc.export_to_markdown()` - Export entire document as markdown string
|
|
|
|
### Text Item Properties
|
|
- `item.text` - The text content
|
|
- `item.label` - Type: title, paragraph, section_header, list_item, etc. (lowercase enum values)
|
|
- `item.prov` - Provenance (page numbers, bounding boxes)
|
|
|
|
### Table Access
|
|
- `table.data.num_rows`, `table.data.num_cols` - Dimensions
|
|
- `table.data.table_cells` - List of TableCell objects
|
|
- `cell.text`, `cell.start_row_offset_idx`, `cell.start_col_offset_idx`
|
|
|
|
### Example Usage
|
|
```python
|
|
doc = get_docling_document("My Document")
|
|
|
|
# Get all headings
|
|
headings = [t.text for t in doc.texts if "header" in str(t.label)]
|
|
|
|
# Iterate with structure
|
|
for item, level in doc.iterate_items():
|
|
print(" " * level + item.text[:50])
|
|
|
|
# Extract table data
|
|
for table in doc.tables:
|
|
for cell in table.data.table_cells:
|
|
print(f"Row {cell.start_row_offset_idx}, Col {cell.start_col_offset_idx}: {cell.text}")
|
|
```
|
|
|
|
## Example Patterns
|
|
|
|
### Counting documents matching a condition
|
|
```python
|
|
docs = list_documents(limit=100)
|
|
count = 0
|
|
for doc in docs:
|
|
content = get_document(doc['id'])
|
|
if content and 'keyword' in content.lower():
|
|
count += 1
|
|
print(f"Found in: {doc['title']}")
|
|
print(f"Total: {count}")
|
|
```
|
|
|
|
### Aggregating data across documents
|
|
```python
|
|
import re
|
|
numbers = []
|
|
results = search("financial data", limit=20)
|
|
for r in results:
|
|
matches = re.findall(r'\$([\d,]+)', r['content'])
|
|
for m in matches:
|
|
numbers.append(int(m.replace(',', '')))
|
|
print(f"Average: ${sum(numbers)/len(numbers):,.2f}")
|
|
```
|
|
|
|
### Using llm() for classification
|
|
```python
|
|
# Get document content
|
|
content = get_document("Q1 Report")
|
|
# Use llm() to classify sentiment
|
|
sentiment = llm(f"Classify the sentiment as positive, negative, or mixed: {content}")
|
|
print(sentiment)
|
|
```
|
|
|
|
## Workflow
|
|
|
|
1. **ALWAYS start by using execute_code** to explore the knowledge base
|
|
2. Run multiple code blocks as needed to gather information
|
|
3. After collecting data, provide your final answer
|
|
|
|
## Output Format
|
|
|
|
CRITICAL: Your final response MUST be valid JSON matching this exact schema:
|
|
```json
|
|
{"answer": "Your complete answer here as a string", "program": "Your final consolidated program here as a string"}
|
|
```
|
|
|
|
- `answer`: A clear answer to the user's question with key findings and references to specific documents/chunks.
|
|
- `program`: A single, self-contained Python program that produces the answer. Consolidate your exploratory code executions into one clean script.
|
|
|
|
Do NOT return arbitrary JSON structures. Always use the exact format: {"answer": "...", "program": "..."}
|
|
|
|
CRITICAL: You MUST call execute_code at least once before providing your answer. Never give up without trying to execute code first.
|
|
role: system
|
|
- content: What is the total revenue across all quarterly reports?
|
|
role: user
|
|
- content: |-
|
|
<think>
|
|
Need to find quarterly reports, extract revenue amounts, sum. Likely documents titled like "Q1 Report", "Q2 Report"... Let's search "quarterly report revenue".
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"results = search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''],
|
|
r[''page_numbers''], r[''score''])\n"}'
|
|
name: execute_code
|
|
id: call_arzz3ioj
|
|
type: function
|
|
- content: '{"code":"results = search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''],
|
|
r[''page_numbers''], r[''score''])\n","stdout":"3\nQ1 Report [] 0.03226645663380623\nQ2 Report [] 0.03226645663380623\nQ3
|
|
Report [] 0.032258063554763794\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_arzz3ioj
|
|
- content: |-
|
|
<think>
|
|
We have 3 reports. Need to extract revenue. Let's fetch each document content and find revenue. Use regex for "$...".
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"import re\nreports = [''Q1 Report'', ''Q2 Report'', ''Q3 Report'']\nrevenues = {}\nfor rep
|
|
in reports:\n content = get_document(rep)\n if content is None:\n # try by title\n for doc
|
|
in list_documents():\n if rep.lower() in doc[''title''].lower():\n content = get_document(doc[''id''])\n break\n if
|
|
content:\n # find patterns like \"Revenue: $1,234,567\"\n matches = re.findall(r''Revenue[:\\s]*\\$([\\d,]+)'',
|
|
content)\n amounts = [int(m.replace('','','''')) for m in matches]\n if amounts:\n revenues[rep]
|
|
= sum(amounts)\n else:\n revenues[rep] = None\n else:\n revenues[rep] = None\nprint(revenues)\n"}'
|
|
name: execute_code
|
|
id: call_vuqzymvs
|
|
type: function
|
|
- content: '{"code":"import re\nreports = [''Q1 Report'', ''Q2 Report'', ''Q3 Report'']\nrevenues = {}\nfor rep in reports:\n content
|
|
= get_document(rep)\n if content is None:\n # try by title\n for doc in list_documents():\n if
|
|
rep.lower() in doc[''title''].lower():\n content = get_document(doc[''id''])\n break\n if
|
|
content:\n # find patterns like \"Revenue: $1,234,567\"\n matches = re.findall(r''Revenue[:\\s]*\\$([\\d,]+)'',
|
|
content)\n amounts = [int(m.replace('','','''')) for m in matches]\n if amounts:\n revenues[rep]
|
|
= sum(amounts)\n else:\n revenues[rep] = None\n else:\n revenues[rep] = None\nprint(revenues)\n","stdout":"{''Q1
|
|
Report'': None, ''Q2 Report'': None, ''Q3 Report'': None}\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_vuqzymvs
|
|
model: gpt-oss
|
|
reasoning_effort: low
|
|
stream: false
|
|
tool_choice: auto
|
|
tools:
|
|
- function:
|
|
description: |-
|
|
<summary>Execute Python code in a Docker-sandboxed environment.
|
|
|
|
The code has access to haiku.rag functions (search, list_documents,
|
|
get_document, get_docling_document, llm) and any Python standard
|
|
library module.
|
|
|
|
Use print() to output results.</summary>
|
|
<returns>
|
|
<description>Structured result with success status, stdout, and stderr.</description>
|
|
</returns>
|
|
name: execute_code
|
|
parameters:
|
|
additionalProperties: false
|
|
properties:
|
|
code:
|
|
description: Python code to execute.
|
|
type: string
|
|
required:
|
|
- code
|
|
type: object
|
|
strict: true
|
|
type: function
|
|
- function:
|
|
description: Result from RLM agent execution.
|
|
name: final_result
|
|
parameters:
|
|
additionalProperties: false
|
|
properties:
|
|
answer:
|
|
description: The answer to the user's question
|
|
type: string
|
|
program:
|
|
description: The final consolidated program
|
|
type: string
|
|
required:
|
|
- answer
|
|
- program
|
|
type: object
|
|
strict: true
|
|
type: function
|
|
uri: http://localhost:11434/v1/chat/completions
|
|
response:
|
|
headers:
|
|
content-length:
|
|
- '626'
|
|
content-type:
|
|
- application/json
|
|
parsed_body:
|
|
choices:
|
|
- finish_reason: tool_calls
|
|
index: 0
|
|
message:
|
|
content: |-
|
|
<think>
|
|
No content or revenue not matched. Let's try list documents to see actual names and perhaps extract via pages.
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"docs = list_documents(limit=50)\nfor d in docs:\n print(d[''title''])\n"}'
|
|
name: execute_code
|
|
id: call_z0mgsixf
|
|
index: 0
|
|
type: function
|
|
created: 1770373353
|
|
id: chatcmpl-25
|
|
model: gpt-oss
|
|
object: chat.completion
|
|
system_fingerprint: fp_ollama
|
|
usage:
|
|
completion_tokens: 70
|
|
prompt_tokens: 2468
|
|
total_tokens: 2538
|
|
status:
|
|
code: 200
|
|
message: OK
|
|
- request:
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '11261'
|
|
content-type:
|
|
- application/json
|
|
host:
|
|
- localhost:11434
|
|
method: POST
|
|
parsed_body:
|
|
messages:
|
|
- content: |-
|
|
You are a Recursive Language Model (RLM) agent that solves complex research questions by writing and executing Python code.
|
|
|
|
IMPORTANT: You MUST use the `execute_code` tool to run Python code. The functions described below are ONLY available inside the execute_code tool - you cannot access them any other way. Always execute code to answer questions; do not just describe what code would do.
|
|
|
|
CRITICAL: Inside execute_code, these functions are ALREADY available in the namespace. Do NOT import them - just use them directly:
|
|
- search("query") ✓ CORRECT
|
|
- from haiku.rag import search ✗ WRONG - will fail
|
|
|
|
You have access to a sandboxed Python environment with these haiku.rag functions (use them directly, no imports needed):
|
|
|
|
## Available Functions
|
|
|
|
### search(query, limit=10) -> list[dict]
|
|
Search the knowledge base using hybrid search (vector + full-text).
|
|
Returns list of dicts with keys: chunk_id, content, document_id, document_title, document_uri, score, page_numbers, headings
|
|
|
|
### list_documents(limit=10, offset=0) -> list[dict]
|
|
List available documents in the knowledge base.
|
|
Returns list of dicts with keys: id, title, uri, created_at
|
|
|
|
### get_document(id_or_title) -> str | None
|
|
Get the full text content of a document by ID, title, or URI.
|
|
Returns the document content as a string, or None if not found.
|
|
|
|
### get_docling_document(id_or_title) -> DoclingDocument | None
|
|
Get the structured DoclingDocument object for advanced analysis.
|
|
Returns a DoclingDocument object, or None if not found.
|
|
See "DoclingDocument API" section below for how to use it.
|
|
|
|
### llm(prompt) -> str
|
|
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
|
|
already have the content and just need LLM reasoning.
|
|
|
|
## Pre-loaded Documents Variable
|
|
|
|
If documents were pre-loaded for this session, a `documents` variable is available:
|
|
```python
|
|
# documents is a list of dicts with keys: id, title, uri, content
|
|
for doc in documents:
|
|
print(doc['title'], len(doc['content']))
|
|
```
|
|
Check if it exists with: `if 'documents' in dir(): ...`
|
|
|
|
## Standard Library Modules
|
|
You can import any Python standard library module.
|
|
|
|
## Strategy Guide
|
|
|
|
1. **Explore First**: Start by listing documents or searching to understand what's available. Document names may differ from filenames (e.g., "tbmed593.pdf" might be stored as "TB MED 593" or similar).
|
|
2. **If get_document returns None**: Use `list_documents()` to see actual document titles, or `search()` to find relevant content.
|
|
3. **Iterative Refinement**: Run code, examine results, adjust your approach based on what you find.
|
|
4. **Use print() Liberally**: The REPL captures stdout - print intermediate results to see what you're working with.
|
|
5. **Aggregate with Code**: For counting, averaging, or comparing across documents, write loops and use collections.
|
|
6. **Use llm() for Classification/Extraction**: When you need to classify, summarize, or extract structured data from content you already have, use llm().
|
|
7. **Cite Your Sources**: Track which documents/chunks informed your answer for citation.
|
|
|
|
## DoclingDocument API
|
|
|
|
When you call `get_docling_document(id_or_title)`, you get a DoclingDocument object for structured document analysis.
|
|
|
|
### Properties
|
|
- `doc.texts` - List of all text items (paragraphs, headings, etc.)
|
|
- `doc.tables` - List of all tables
|
|
- `doc.pictures` - List of all pictures/figures
|
|
- `doc.name` - Document name
|
|
|
|
### Methods
|
|
- `doc.iterate_items(with_groups=False)` - Iterate all items with hierarchy level
|
|
Returns tuples of (item, level) where level is nesting depth
|
|
- `doc.export_to_markdown()` - Export entire document as markdown string
|
|
|
|
### Text Item Properties
|
|
- `item.text` - The text content
|
|
- `item.label` - Type: title, paragraph, section_header, list_item, etc. (lowercase enum values)
|
|
- `item.prov` - Provenance (page numbers, bounding boxes)
|
|
|
|
### Table Access
|
|
- `table.data.num_rows`, `table.data.num_cols` - Dimensions
|
|
- `table.data.table_cells` - List of TableCell objects
|
|
- `cell.text`, `cell.start_row_offset_idx`, `cell.start_col_offset_idx`
|
|
|
|
### Example Usage
|
|
```python
|
|
doc = get_docling_document("My Document")
|
|
|
|
# Get all headings
|
|
headings = [t.text for t in doc.texts if "header" in str(t.label)]
|
|
|
|
# Iterate with structure
|
|
for item, level in doc.iterate_items():
|
|
print(" " * level + item.text[:50])
|
|
|
|
# Extract table data
|
|
for table in doc.tables:
|
|
for cell in table.data.table_cells:
|
|
print(f"Row {cell.start_row_offset_idx}, Col {cell.start_col_offset_idx}: {cell.text}")
|
|
```
|
|
|
|
## Example Patterns
|
|
|
|
### Counting documents matching a condition
|
|
```python
|
|
docs = list_documents(limit=100)
|
|
count = 0
|
|
for doc in docs:
|
|
content = get_document(doc['id'])
|
|
if content and 'keyword' in content.lower():
|
|
count += 1
|
|
print(f"Found in: {doc['title']}")
|
|
print(f"Total: {count}")
|
|
```
|
|
|
|
### Aggregating data across documents
|
|
```python
|
|
import re
|
|
numbers = []
|
|
results = search("financial data", limit=20)
|
|
for r in results:
|
|
matches = re.findall(r'\$([\d,]+)', r['content'])
|
|
for m in matches:
|
|
numbers.append(int(m.replace(',', '')))
|
|
print(f"Average: ${sum(numbers)/len(numbers):,.2f}")
|
|
```
|
|
|
|
### Using llm() for classification
|
|
```python
|
|
# Get document content
|
|
content = get_document("Q1 Report")
|
|
# Use llm() to classify sentiment
|
|
sentiment = llm(f"Classify the sentiment as positive, negative, or mixed: {content}")
|
|
print(sentiment)
|
|
```
|
|
|
|
## Workflow
|
|
|
|
1. **ALWAYS start by using execute_code** to explore the knowledge base
|
|
2. Run multiple code blocks as needed to gather information
|
|
3. After collecting data, provide your final answer
|
|
|
|
## Output Format
|
|
|
|
CRITICAL: Your final response MUST be valid JSON matching this exact schema:
|
|
```json
|
|
{"answer": "Your complete answer here as a string", "program": "Your final consolidated program here as a string"}
|
|
```
|
|
|
|
- `answer`: A clear answer to the user's question with key findings and references to specific documents/chunks.
|
|
- `program`: A single, self-contained Python program that produces the answer. Consolidate your exploratory code executions into one clean script.
|
|
|
|
Do NOT return arbitrary JSON structures. Always use the exact format: {"answer": "...", "program": "..."}
|
|
|
|
CRITICAL: You MUST call execute_code at least once before providing your answer. Never give up without trying to execute code first.
|
|
role: system
|
|
- content: What is the total revenue across all quarterly reports?
|
|
role: user
|
|
- content: |-
|
|
<think>
|
|
Need to find quarterly reports, extract revenue amounts, sum. Likely documents titled like "Q1 Report", "Q2 Report"... Let's search "quarterly report revenue".
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"results = search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''],
|
|
r[''page_numbers''], r[''score''])\n"}'
|
|
name: execute_code
|
|
id: call_arzz3ioj
|
|
type: function
|
|
- content: '{"code":"results = search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''],
|
|
r[''page_numbers''], r[''score''])\n","stdout":"3\nQ1 Report [] 0.03226645663380623\nQ2 Report [] 0.03226645663380623\nQ3
|
|
Report [] 0.032258063554763794\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_arzz3ioj
|
|
- content: |-
|
|
<think>
|
|
We have 3 reports. Need to extract revenue. Let's fetch each document content and find revenue. Use regex for "$...".
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"import re\nreports = [''Q1 Report'', ''Q2 Report'', ''Q3 Report'']\nrevenues = {}\nfor rep
|
|
in reports:\n content = get_document(rep)\n if content is None:\n # try by title\n for doc
|
|
in list_documents():\n if rep.lower() in doc[''title''].lower():\n content = get_document(doc[''id''])\n break\n if
|
|
content:\n # find patterns like \"Revenue: $1,234,567\"\n matches = re.findall(r''Revenue[:\\s]*\\$([\\d,]+)'',
|
|
content)\n amounts = [int(m.replace('','','''')) for m in matches]\n if amounts:\n revenues[rep]
|
|
= sum(amounts)\n else:\n revenues[rep] = None\n else:\n revenues[rep] = None\nprint(revenues)\n"}'
|
|
name: execute_code
|
|
id: call_vuqzymvs
|
|
type: function
|
|
- content: '{"code":"import re\nreports = [''Q1 Report'', ''Q2 Report'', ''Q3 Report'']\nrevenues = {}\nfor rep in reports:\n content
|
|
= get_document(rep)\n if content is None:\n # try by title\n for doc in list_documents():\n if
|
|
rep.lower() in doc[''title''].lower():\n content = get_document(doc[''id''])\n break\n if
|
|
content:\n # find patterns like \"Revenue: $1,234,567\"\n matches = re.findall(r''Revenue[:\\s]*\\$([\\d,]+)'',
|
|
content)\n amounts = [int(m.replace('','','''')) for m in matches]\n if amounts:\n revenues[rep]
|
|
= sum(amounts)\n else:\n revenues[rep] = None\n else:\n revenues[rep] = None\nprint(revenues)\n","stdout":"{''Q1
|
|
Report'': None, ''Q2 Report'': None, ''Q3 Report'': None}\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_vuqzymvs
|
|
- content: |2-
|
|
|
|
No content or revenue not matched. Let's try list documents to see actual names and perhaps extract via pages.
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"docs = list_documents(limit=50)\nfor d in docs:\n print(d[''title''])\n"}'
|
|
name: execute_code
|
|
id: call_z0mgsixf
|
|
type: function
|
|
- content: '{"code":"docs = list_documents(limit=50)\nfor d in docs:\n print(d[''title''])\n","stdout":"Q1 Report\nQ2
|
|
Report\nQ3 Report\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_z0mgsixf
|
|
model: gpt-oss
|
|
reasoning_effort: low
|
|
stream: false
|
|
tool_choice: auto
|
|
tools:
|
|
- function:
|
|
description: |-
|
|
<summary>Execute Python code in a Docker-sandboxed environment.
|
|
|
|
The code has access to haiku.rag functions (search, list_documents,
|
|
get_document, get_docling_document, llm) and any Python standard
|
|
library module.
|
|
|
|
Use print() to output results.</summary>
|
|
<returns>
|
|
<description>Structured result with success status, stdout, and stderr.</description>
|
|
</returns>
|
|
name: execute_code
|
|
parameters:
|
|
additionalProperties: false
|
|
properties:
|
|
code:
|
|
description: Python code to execute.
|
|
type: string
|
|
required:
|
|
- code
|
|
type: object
|
|
strict: true
|
|
type: function
|
|
- function:
|
|
description: Result from RLM agent execution.
|
|
name: final_result
|
|
parameters:
|
|
additionalProperties: false
|
|
properties:
|
|
answer:
|
|
description: The answer to the user's question
|
|
type: string
|
|
program:
|
|
description: The final consolidated program
|
|
type: string
|
|
required:
|
|
- answer
|
|
- program
|
|
type: object
|
|
strict: true
|
|
type: function
|
|
uri: http://localhost:11434/v1/chat/completions
|
|
response:
|
|
headers:
|
|
content-length:
|
|
- '859'
|
|
content-type:
|
|
- application/json
|
|
parsed_body:
|
|
choices:
|
|
- finish_reason: tool_calls
|
|
index: 0
|
|
message:
|
|
content: ''
|
|
reasoning: Maybe revenue is in tables. Use docling.
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"doc = get_docling_document(''Q1 Report'')\nprint(doc.name)\n# print headings\nheadings
|
|
= [t.text for t in doc.texts if ''header'' in str(t.label)]\nprint(''headings:'', headlines:=headings[:5])\n#
|
|
find tables\nprint(f\"Tables: {len(doc.tables)}\")\nfor i,table in enumerate(doc.tables):\n print(f\"Table
|
|
{i} rows {table.data.num_rows} cols {table.data.num_cols}\")\n"}'
|
|
name: execute_code
|
|
id: call_acbn2mdz
|
|
index: 0
|
|
type: function
|
|
created: 1770373356
|
|
id: chatcmpl-268
|
|
model: gpt-oss
|
|
object: chat.completion
|
|
system_fingerprint: fp_ollama
|
|
usage:
|
|
completion_tokens: 145
|
|
prompt_tokens: 2595
|
|
total_tokens: 2740
|
|
status:
|
|
code: 200
|
|
message: OK
|
|
- request:
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '12396'
|
|
content-type:
|
|
- application/json
|
|
host:
|
|
- localhost:11434
|
|
method: POST
|
|
parsed_body:
|
|
messages:
|
|
- content: |-
|
|
You are a Recursive Language Model (RLM) agent that solves complex research questions by writing and executing Python code.
|
|
|
|
IMPORTANT: You MUST use the `execute_code` tool to run Python code. The functions described below are ONLY available inside the execute_code tool - you cannot access them any other way. Always execute code to answer questions; do not just describe what code would do.
|
|
|
|
CRITICAL: Inside execute_code, these functions are ALREADY available in the namespace. Do NOT import them - just use them directly:
|
|
- search("query") ✓ CORRECT
|
|
- from haiku.rag import search ✗ WRONG - will fail
|
|
|
|
You have access to a sandboxed Python environment with these haiku.rag functions (use them directly, no imports needed):
|
|
|
|
## Available Functions
|
|
|
|
### search(query, limit=10) -> list[dict]
|
|
Search the knowledge base using hybrid search (vector + full-text).
|
|
Returns list of dicts with keys: chunk_id, content, document_id, document_title, document_uri, score, page_numbers, headings
|
|
|
|
### list_documents(limit=10, offset=0) -> list[dict]
|
|
List available documents in the knowledge base.
|
|
Returns list of dicts with keys: id, title, uri, created_at
|
|
|
|
### get_document(id_or_title) -> str | None
|
|
Get the full text content of a document by ID, title, or URI.
|
|
Returns the document content as a string, or None if not found.
|
|
|
|
### get_docling_document(id_or_title) -> DoclingDocument | None
|
|
Get the structured DoclingDocument object for advanced analysis.
|
|
Returns a DoclingDocument object, or None if not found.
|
|
See "DoclingDocument API" section below for how to use it.
|
|
|
|
### llm(prompt) -> str
|
|
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
|
|
already have the content and just need LLM reasoning.
|
|
|
|
## Pre-loaded Documents Variable
|
|
|
|
If documents were pre-loaded for this session, a `documents` variable is available:
|
|
```python
|
|
# documents is a list of dicts with keys: id, title, uri, content
|
|
for doc in documents:
|
|
print(doc['title'], len(doc['content']))
|
|
```
|
|
Check if it exists with: `if 'documents' in dir(): ...`
|
|
|
|
## Standard Library Modules
|
|
You can import any Python standard library module.
|
|
|
|
## Strategy Guide
|
|
|
|
1. **Explore First**: Start by listing documents or searching to understand what's available. Document names may differ from filenames (e.g., "tbmed593.pdf" might be stored as "TB MED 593" or similar).
|
|
2. **If get_document returns None**: Use `list_documents()` to see actual document titles, or `search()` to find relevant content.
|
|
3. **Iterative Refinement**: Run code, examine results, adjust your approach based on what you find.
|
|
4. **Use print() Liberally**: The REPL captures stdout - print intermediate results to see what you're working with.
|
|
5. **Aggregate with Code**: For counting, averaging, or comparing across documents, write loops and use collections.
|
|
6. **Use llm() for Classification/Extraction**: When you need to classify, summarize, or extract structured data from content you already have, use llm().
|
|
7. **Cite Your Sources**: Track which documents/chunks informed your answer for citation.
|
|
|
|
## DoclingDocument API
|
|
|
|
When you call `get_docling_document(id_or_title)`, you get a DoclingDocument object for structured document analysis.
|
|
|
|
### Properties
|
|
- `doc.texts` - List of all text items (paragraphs, headings, etc.)
|
|
- `doc.tables` - List of all tables
|
|
- `doc.pictures` - List of all pictures/figures
|
|
- `doc.name` - Document name
|
|
|
|
### Methods
|
|
- `doc.iterate_items(with_groups=False)` - Iterate all items with hierarchy level
|
|
Returns tuples of (item, level) where level is nesting depth
|
|
- `doc.export_to_markdown()` - Export entire document as markdown string
|
|
|
|
### Text Item Properties
|
|
- `item.text` - The text content
|
|
- `item.label` - Type: title, paragraph, section_header, list_item, etc. (lowercase enum values)
|
|
- `item.prov` - Provenance (page numbers, bounding boxes)
|
|
|
|
### Table Access
|
|
- `table.data.num_rows`, `table.data.num_cols` - Dimensions
|
|
- `table.data.table_cells` - List of TableCell objects
|
|
- `cell.text`, `cell.start_row_offset_idx`, `cell.start_col_offset_idx`
|
|
|
|
### Example Usage
|
|
```python
|
|
doc = get_docling_document("My Document")
|
|
|
|
# Get all headings
|
|
headings = [t.text for t in doc.texts if "header" in str(t.label)]
|
|
|
|
# Iterate with structure
|
|
for item, level in doc.iterate_items():
|
|
print(" " * level + item.text[:50])
|
|
|
|
# Extract table data
|
|
for table in doc.tables:
|
|
for cell in table.data.table_cells:
|
|
print(f"Row {cell.start_row_offset_idx}, Col {cell.start_col_offset_idx}: {cell.text}")
|
|
```
|
|
|
|
## Example Patterns
|
|
|
|
### Counting documents matching a condition
|
|
```python
|
|
docs = list_documents(limit=100)
|
|
count = 0
|
|
for doc in docs:
|
|
content = get_document(doc['id'])
|
|
if content and 'keyword' in content.lower():
|
|
count += 1
|
|
print(f"Found in: {doc['title']}")
|
|
print(f"Total: {count}")
|
|
```
|
|
|
|
### Aggregating data across documents
|
|
```python
|
|
import re
|
|
numbers = []
|
|
results = search("financial data", limit=20)
|
|
for r in results:
|
|
matches = re.findall(r'\$([\d,]+)', r['content'])
|
|
for m in matches:
|
|
numbers.append(int(m.replace(',', '')))
|
|
print(f"Average: ${sum(numbers)/len(numbers):,.2f}")
|
|
```
|
|
|
|
### Using llm() for classification
|
|
```python
|
|
# Get document content
|
|
content = get_document("Q1 Report")
|
|
# Use llm() to classify sentiment
|
|
sentiment = llm(f"Classify the sentiment as positive, negative, or mixed: {content}")
|
|
print(sentiment)
|
|
```
|
|
|
|
## Workflow
|
|
|
|
1. **ALWAYS start by using execute_code** to explore the knowledge base
|
|
2. Run multiple code blocks as needed to gather information
|
|
3. After collecting data, provide your final answer
|
|
|
|
## Output Format
|
|
|
|
CRITICAL: Your final response MUST be valid JSON matching this exact schema:
|
|
```json
|
|
{"answer": "Your complete answer here as a string", "program": "Your final consolidated program here as a string"}
|
|
```
|
|
|
|
- `answer`: A clear answer to the user's question with key findings and references to specific documents/chunks.
|
|
- `program`: A single, self-contained Python program that produces the answer. Consolidate your exploratory code executions into one clean script.
|
|
|
|
Do NOT return arbitrary JSON structures. Always use the exact format: {"answer": "...", "program": "..."}
|
|
|
|
CRITICAL: You MUST call execute_code at least once before providing your answer. Never give up without trying to execute code first.
|
|
role: system
|
|
- content: What is the total revenue across all quarterly reports?
|
|
role: user
|
|
- content: |-
|
|
<think>
|
|
Need to find quarterly reports, extract revenue amounts, sum. Likely documents titled like "Q1 Report", "Q2 Report"... Let's search "quarterly report revenue".
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"results = search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''],
|
|
r[''page_numbers''], r[''score''])\n"}'
|
|
name: execute_code
|
|
id: call_arzz3ioj
|
|
type: function
|
|
- content: '{"code":"results = search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''],
|
|
r[''page_numbers''], r[''score''])\n","stdout":"3\nQ1 Report [] 0.03226645663380623\nQ2 Report [] 0.03226645663380623\nQ3
|
|
Report [] 0.032258063554763794\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_arzz3ioj
|
|
- content: |-
|
|
<think>
|
|
We have 3 reports. Need to extract revenue. Let's fetch each document content and find revenue. Use regex for "$...".
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"import re\nreports = [''Q1 Report'', ''Q2 Report'', ''Q3 Report'']\nrevenues = {}\nfor rep
|
|
in reports:\n content = get_document(rep)\n if content is None:\n # try by title\n for doc
|
|
in list_documents():\n if rep.lower() in doc[''title''].lower():\n content = get_document(doc[''id''])\n break\n if
|
|
content:\n # find patterns like \"Revenue: $1,234,567\"\n matches = re.findall(r''Revenue[:\\s]*\\$([\\d,]+)'',
|
|
content)\n amounts = [int(m.replace('','','''')) for m in matches]\n if amounts:\n revenues[rep]
|
|
= sum(amounts)\n else:\n revenues[rep] = None\n else:\n revenues[rep] = None\nprint(revenues)\n"}'
|
|
name: execute_code
|
|
id: call_vuqzymvs
|
|
type: function
|
|
- content: '{"code":"import re\nreports = [''Q1 Report'', ''Q2 Report'', ''Q3 Report'']\nrevenues = {}\nfor rep in reports:\n content
|
|
= get_document(rep)\n if content is None:\n # try by title\n for doc in list_documents():\n if
|
|
rep.lower() in doc[''title''].lower():\n content = get_document(doc[''id''])\n break\n if
|
|
content:\n # find patterns like \"Revenue: $1,234,567\"\n matches = re.findall(r''Revenue[:\\s]*\\$([\\d,]+)'',
|
|
content)\n amounts = [int(m.replace('','','''')) for m in matches]\n if amounts:\n revenues[rep]
|
|
= sum(amounts)\n else:\n revenues[rep] = None\n else:\n revenues[rep] = None\nprint(revenues)\n","stdout":"{''Q1
|
|
Report'': None, ''Q2 Report'': None, ''Q3 Report'': None}\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_vuqzymvs
|
|
- content: |2-
|
|
|
|
No content or revenue not matched. Let's try list documents to see actual names and perhaps extract via pages.
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"docs = list_documents(limit=50)\nfor d in docs:\n print(d[''title''])\n"}'
|
|
name: execute_code
|
|
id: call_z0mgsixf
|
|
type: function
|
|
- content: '{"code":"docs = list_documents(limit=50)\nfor d in docs:\n print(d[''title''])\n","stdout":"Q1 Report\nQ2
|
|
Report\nQ3 Report\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_z0mgsixf
|
|
- content: |-
|
|
<think>
|
|
Maybe revenue is in tables. Use docling.
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"doc = get_docling_document(''Q1 Report'')\nprint(doc.name)\n# print headings\nheadings =
|
|
[t.text for t in doc.texts if ''header'' in str(t.label)]\nprint(''headings:'', headlines:=headings[:5])\n#
|
|
find tables\nprint(f\"Tables: {len(doc.tables)}\")\nfor i,table in enumerate(doc.tables):\n print(f\"Table
|
|
{i} rows {table.data.num_rows} cols {table.data.num_cols}\")\n"}'
|
|
name: execute_code
|
|
id: call_acbn2mdz
|
|
type: function
|
|
- content: '{"code":"doc = get_docling_document(''Q1 Report'')\nprint(doc.name)\n# print headings\nheadings = [t.text
|
|
for t in doc.texts if ''header'' in str(t.label)]\nprint(''headings:'', headlines:=headings[:5])\n# find tables\nprint(f\"Tables:
|
|
{len(doc.tables)}\")\nfor i,table in enumerate(doc.tables):\n print(f\"Table {i} rows {table.data.num_rows} cols
|
|
{table.data.num_cols}\")\n","stdout":"content\nheadings: []\nTables: 0\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_acbn2mdz
|
|
model: gpt-oss
|
|
reasoning_effort: low
|
|
stream: false
|
|
tool_choice: auto
|
|
tools:
|
|
- function:
|
|
description: |-
|
|
<summary>Execute Python code in a Docker-sandboxed environment.
|
|
|
|
The code has access to haiku.rag functions (search, list_documents,
|
|
get_document, get_docling_document, llm) and any Python standard
|
|
library module.
|
|
|
|
Use print() to output results.</summary>
|
|
<returns>
|
|
<description>Structured result with success status, stdout, and stderr.</description>
|
|
</returns>
|
|
name: execute_code
|
|
parameters:
|
|
additionalProperties: false
|
|
properties:
|
|
code:
|
|
description: Python code to execute.
|
|
type: string
|
|
required:
|
|
- code
|
|
type: object
|
|
strict: true
|
|
type: function
|
|
- function:
|
|
description: Result from RLM agent execution.
|
|
name: final_result
|
|
parameters:
|
|
additionalProperties: false
|
|
properties:
|
|
answer:
|
|
description: The answer to the user's question
|
|
type: string
|
|
program:
|
|
description: The final consolidated program
|
|
type: string
|
|
required:
|
|
- answer
|
|
- program
|
|
type: object
|
|
strict: true
|
|
type: function
|
|
uri: http://localhost:11434/v1/chat/completions
|
|
response:
|
|
headers:
|
|
content-length:
|
|
- '643'
|
|
content-type:
|
|
- application/json
|
|
parsed_body:
|
|
choices:
|
|
- finish_reason: tool_calls
|
|
index: 0
|
|
message:
|
|
content: ''
|
|
reasoning: No tables. Probably revenue mentioned in paragraphs. Let's fetch entire content and search for "$".
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"content = get_document(''Q1 Report'')\nprint(content[:500])\nprint(''...'')\nprint(content.count(''$''))\n"}'
|
|
name: execute_code
|
|
id: call_y1fiwuj8
|
|
index: 0
|
|
type: function
|
|
created: 1770373358
|
|
id: chatcmpl-409
|
|
model: gpt-oss
|
|
object: chat.completion
|
|
system_fingerprint: fp_ollama
|
|
usage:
|
|
completion_tokens: 72
|
|
prompt_tokens: 2895
|
|
total_tokens: 2967
|
|
status:
|
|
code: 200
|
|
message: OK
|
|
- request:
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '13054'
|
|
content-type:
|
|
- application/json
|
|
host:
|
|
- localhost:11434
|
|
method: POST
|
|
parsed_body:
|
|
messages:
|
|
- content: |-
|
|
You are a Recursive Language Model (RLM) agent that solves complex research questions by writing and executing Python code.
|
|
|
|
IMPORTANT: You MUST use the `execute_code` tool to run Python code. The functions described below are ONLY available inside the execute_code tool - you cannot access them any other way. Always execute code to answer questions; do not just describe what code would do.
|
|
|
|
CRITICAL: Inside execute_code, these functions are ALREADY available in the namespace. Do NOT import them - just use them directly:
|
|
- search("query") ✓ CORRECT
|
|
- from haiku.rag import search ✗ WRONG - will fail
|
|
|
|
You have access to a sandboxed Python environment with these haiku.rag functions (use them directly, no imports needed):
|
|
|
|
## Available Functions
|
|
|
|
### search(query, limit=10) -> list[dict]
|
|
Search the knowledge base using hybrid search (vector + full-text).
|
|
Returns list of dicts with keys: chunk_id, content, document_id, document_title, document_uri, score, page_numbers, headings
|
|
|
|
### list_documents(limit=10, offset=0) -> list[dict]
|
|
List available documents in the knowledge base.
|
|
Returns list of dicts with keys: id, title, uri, created_at
|
|
|
|
### get_document(id_or_title) -> str | None
|
|
Get the full text content of a document by ID, title, or URI.
|
|
Returns the document content as a string, or None if not found.
|
|
|
|
### get_docling_document(id_or_title) -> DoclingDocument | None
|
|
Get the structured DoclingDocument object for advanced analysis.
|
|
Returns a DoclingDocument object, or None if not found.
|
|
See "DoclingDocument API" section below for how to use it.
|
|
|
|
### llm(prompt) -> str
|
|
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
|
|
already have the content and just need LLM reasoning.
|
|
|
|
## Pre-loaded Documents Variable
|
|
|
|
If documents were pre-loaded for this session, a `documents` variable is available:
|
|
```python
|
|
# documents is a list of dicts with keys: id, title, uri, content
|
|
for doc in documents:
|
|
print(doc['title'], len(doc['content']))
|
|
```
|
|
Check if it exists with: `if 'documents' in dir(): ...`
|
|
|
|
## Standard Library Modules
|
|
You can import any Python standard library module.
|
|
|
|
## Strategy Guide
|
|
|
|
1. **Explore First**: Start by listing documents or searching to understand what's available. Document names may differ from filenames (e.g., "tbmed593.pdf" might be stored as "TB MED 593" or similar).
|
|
2. **If get_document returns None**: Use `list_documents()` to see actual document titles, or `search()` to find relevant content.
|
|
3. **Iterative Refinement**: Run code, examine results, adjust your approach based on what you find.
|
|
4. **Use print() Liberally**: The REPL captures stdout - print intermediate results to see what you're working with.
|
|
5. **Aggregate with Code**: For counting, averaging, or comparing across documents, write loops and use collections.
|
|
6. **Use llm() for Classification/Extraction**: When you need to classify, summarize, or extract structured data from content you already have, use llm().
|
|
7. **Cite Your Sources**: Track which documents/chunks informed your answer for citation.
|
|
|
|
## DoclingDocument API
|
|
|
|
When you call `get_docling_document(id_or_title)`, you get a DoclingDocument object for structured document analysis.
|
|
|
|
### Properties
|
|
- `doc.texts` - List of all text items (paragraphs, headings, etc.)
|
|
- `doc.tables` - List of all tables
|
|
- `doc.pictures` - List of all pictures/figures
|
|
- `doc.name` - Document name
|
|
|
|
### Methods
|
|
- `doc.iterate_items(with_groups=False)` - Iterate all items with hierarchy level
|
|
Returns tuples of (item, level) where level is nesting depth
|
|
- `doc.export_to_markdown()` - Export entire document as markdown string
|
|
|
|
### Text Item Properties
|
|
- `item.text` - The text content
|
|
- `item.label` - Type: title, paragraph, section_header, list_item, etc. (lowercase enum values)
|
|
- `item.prov` - Provenance (page numbers, bounding boxes)
|
|
|
|
### Table Access
|
|
- `table.data.num_rows`, `table.data.num_cols` - Dimensions
|
|
- `table.data.table_cells` - List of TableCell objects
|
|
- `cell.text`, `cell.start_row_offset_idx`, `cell.start_col_offset_idx`
|
|
|
|
### Example Usage
|
|
```python
|
|
doc = get_docling_document("My Document")
|
|
|
|
# Get all headings
|
|
headings = [t.text for t in doc.texts if "header" in str(t.label)]
|
|
|
|
# Iterate with structure
|
|
for item, level in doc.iterate_items():
|
|
print(" " * level + item.text[:50])
|
|
|
|
# Extract table data
|
|
for table in doc.tables:
|
|
for cell in table.data.table_cells:
|
|
print(f"Row {cell.start_row_offset_idx}, Col {cell.start_col_offset_idx}: {cell.text}")
|
|
```
|
|
|
|
## Example Patterns
|
|
|
|
### Counting documents matching a condition
|
|
```python
|
|
docs = list_documents(limit=100)
|
|
count = 0
|
|
for doc in docs:
|
|
content = get_document(doc['id'])
|
|
if content and 'keyword' in content.lower():
|
|
count += 1
|
|
print(f"Found in: {doc['title']}")
|
|
print(f"Total: {count}")
|
|
```
|
|
|
|
### Aggregating data across documents
|
|
```python
|
|
import re
|
|
numbers = []
|
|
results = search("financial data", limit=20)
|
|
for r in results:
|
|
matches = re.findall(r'\$([\d,]+)', r['content'])
|
|
for m in matches:
|
|
numbers.append(int(m.replace(',', '')))
|
|
print(f"Average: ${sum(numbers)/len(numbers):,.2f}")
|
|
```
|
|
|
|
### Using llm() for classification
|
|
```python
|
|
# Get document content
|
|
content = get_document("Q1 Report")
|
|
# Use llm() to classify sentiment
|
|
sentiment = llm(f"Classify the sentiment as positive, negative, or mixed: {content}")
|
|
print(sentiment)
|
|
```
|
|
|
|
## Workflow
|
|
|
|
1. **ALWAYS start by using execute_code** to explore the knowledge base
|
|
2. Run multiple code blocks as needed to gather information
|
|
3. After collecting data, provide your final answer
|
|
|
|
## Output Format
|
|
|
|
CRITICAL: Your final response MUST be valid JSON matching this exact schema:
|
|
```json
|
|
{"answer": "Your complete answer here as a string", "program": "Your final consolidated program here as a string"}
|
|
```
|
|
|
|
- `answer`: A clear answer to the user's question with key findings and references to specific documents/chunks.
|
|
- `program`: A single, self-contained Python program that produces the answer. Consolidate your exploratory code executions into one clean script.
|
|
|
|
Do NOT return arbitrary JSON structures. Always use the exact format: {"answer": "...", "program": "..."}
|
|
|
|
CRITICAL: You MUST call execute_code at least once before providing your answer. Never give up without trying to execute code first.
|
|
role: system
|
|
- content: What is the total revenue across all quarterly reports?
|
|
role: user
|
|
- content: |-
|
|
<think>
|
|
Need to find quarterly reports, extract revenue amounts, sum. Likely documents titled like "Q1 Report", "Q2 Report"... Let's search "quarterly report revenue".
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"results = search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''],
|
|
r[''page_numbers''], r[''score''])\n"}'
|
|
name: execute_code
|
|
id: call_arzz3ioj
|
|
type: function
|
|
- content: '{"code":"results = search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''],
|
|
r[''page_numbers''], r[''score''])\n","stdout":"3\nQ1 Report [] 0.03226645663380623\nQ2 Report [] 0.03226645663380623\nQ3
|
|
Report [] 0.032258063554763794\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_arzz3ioj
|
|
- content: |-
|
|
<think>
|
|
We have 3 reports. Need to extract revenue. Let's fetch each document content and find revenue. Use regex for "$...".
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"import re\nreports = [''Q1 Report'', ''Q2 Report'', ''Q3 Report'']\nrevenues = {}\nfor rep
|
|
in reports:\n content = get_document(rep)\n if content is None:\n # try by title\n for doc
|
|
in list_documents():\n if rep.lower() in doc[''title''].lower():\n content = get_document(doc[''id''])\n break\n if
|
|
content:\n # find patterns like \"Revenue: $1,234,567\"\n matches = re.findall(r''Revenue[:\\s]*\\$([\\d,]+)'',
|
|
content)\n amounts = [int(m.replace('','','''')) for m in matches]\n if amounts:\n revenues[rep]
|
|
= sum(amounts)\n else:\n revenues[rep] = None\n else:\n revenues[rep] = None\nprint(revenues)\n"}'
|
|
name: execute_code
|
|
id: call_vuqzymvs
|
|
type: function
|
|
- content: '{"code":"import re\nreports = [''Q1 Report'', ''Q2 Report'', ''Q3 Report'']\nrevenues = {}\nfor rep in reports:\n content
|
|
= get_document(rep)\n if content is None:\n # try by title\n for doc in list_documents():\n if
|
|
rep.lower() in doc[''title''].lower():\n content = get_document(doc[''id''])\n break\n if
|
|
content:\n # find patterns like \"Revenue: $1,234,567\"\n matches = re.findall(r''Revenue[:\\s]*\\$([\\d,]+)'',
|
|
content)\n amounts = [int(m.replace('','','''')) for m in matches]\n if amounts:\n revenues[rep]
|
|
= sum(amounts)\n else:\n revenues[rep] = None\n else:\n revenues[rep] = None\nprint(revenues)\n","stdout":"{''Q1
|
|
Report'': None, ''Q2 Report'': None, ''Q3 Report'': None}\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_vuqzymvs
|
|
- content: |2-
|
|
|
|
No content or revenue not matched. Let's try list documents to see actual names and perhaps extract via pages.
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"docs = list_documents(limit=50)\nfor d in docs:\n print(d[''title''])\n"}'
|
|
name: execute_code
|
|
id: call_z0mgsixf
|
|
type: function
|
|
- content: '{"code":"docs = list_documents(limit=50)\nfor d in docs:\n print(d[''title''])\n","stdout":"Q1 Report\nQ2
|
|
Report\nQ3 Report\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_z0mgsixf
|
|
- content: |-
|
|
<think>
|
|
Maybe revenue is in tables. Use docling.
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"doc = get_docling_document(''Q1 Report'')\nprint(doc.name)\n# print headings\nheadings =
|
|
[t.text for t in doc.texts if ''header'' in str(t.label)]\nprint(''headings:'', headlines:=headings[:5])\n#
|
|
find tables\nprint(f\"Tables: {len(doc.tables)}\")\nfor i,table in enumerate(doc.tables):\n print(f\"Table
|
|
{i} rows {table.data.num_rows} cols {table.data.num_cols}\")\n"}'
|
|
name: execute_code
|
|
id: call_acbn2mdz
|
|
type: function
|
|
- content: '{"code":"doc = get_docling_document(''Q1 Report'')\nprint(doc.name)\n# print headings\nheadings = [t.text
|
|
for t in doc.texts if ''header'' in str(t.label)]\nprint(''headings:'', headlines:=headings[:5])\n# find tables\nprint(f\"Tables:
|
|
{len(doc.tables)}\")\nfor i,table in enumerate(doc.tables):\n print(f\"Table {i} rows {table.data.num_rows} cols
|
|
{table.data.num_cols}\")\n","stdout":"content\nheadings: []\nTables: 0\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_acbn2mdz
|
|
- content: |-
|
|
<think>
|
|
No tables. Probably revenue mentioned in paragraphs. Let's fetch entire content and search for "$".
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"content = get_document(''Q1 Report'')\nprint(content[:500])\nprint(''...'')\nprint(content.count(''$''))\n"}'
|
|
name: execute_code
|
|
id: call_y1fiwuj8
|
|
type: function
|
|
- content: '{"code":"content = get_document(''Q1 Report'')\nprint(content[:500])\nprint(''...'')\nprint(content.count(''$''))\n","stdout":"Sales
|
|
report Q1: Revenue was $100,000.\n...\n1\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_y1fiwuj8
|
|
model: gpt-oss
|
|
reasoning_effort: low
|
|
stream: false
|
|
tool_choice: auto
|
|
tools:
|
|
- function:
|
|
description: |-
|
|
<summary>Execute Python code in a Docker-sandboxed environment.
|
|
|
|
The code has access to haiku.rag functions (search, list_documents,
|
|
get_document, get_docling_document, llm) and any Python standard
|
|
library module.
|
|
|
|
Use print() to output results.</summary>
|
|
<returns>
|
|
<description>Structured result with success status, stdout, and stderr.</description>
|
|
</returns>
|
|
name: execute_code
|
|
parameters:
|
|
additionalProperties: false
|
|
properties:
|
|
code:
|
|
description: Python code to execute.
|
|
type: string
|
|
required:
|
|
- code
|
|
type: object
|
|
strict: true
|
|
type: function
|
|
- function:
|
|
description: Result from RLM agent execution.
|
|
name: final_result
|
|
parameters:
|
|
additionalProperties: false
|
|
properties:
|
|
answer:
|
|
description: The answer to the user's question
|
|
type: string
|
|
program:
|
|
description: The final consolidated program
|
|
type: string
|
|
required:
|
|
- answer
|
|
- program
|
|
type: object
|
|
strict: true
|
|
type: function
|
|
uri: http://localhost:11434/v1/chat/completions
|
|
response:
|
|
headers:
|
|
content-length:
|
|
- '646'
|
|
content-type:
|
|
- application/json
|
|
parsed_body:
|
|
choices:
|
|
- finish_reason: tool_calls
|
|
index: 0
|
|
message:
|
|
content: ''
|
|
reasoning: Now extract $ amounts.
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"import re\ncontent = get_document(''Q1 Report'')\namounts = re.findall(r''\\$(\\d{1,3}(?:,\\d{3})*)'',
|
|
content)\nprint(amounts)\nprint([int(a.replace('','','''')) for a in amounts])\n"}'
|
|
name: execute_code
|
|
id: call_i5cijc97
|
|
index: 0
|
|
type: function
|
|
created: 1770373360
|
|
id: chatcmpl-728
|
|
model: gpt-oss
|
|
object: chat.completion
|
|
system_fingerprint: fp_ollama
|
|
usage:
|
|
completion_tokens: 90
|
|
prompt_tokens: 3045
|
|
total_tokens: 3135
|
|
status:
|
|
code: 200
|
|
message: OK
|
|
- request:
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '13771'
|
|
content-type:
|
|
- application/json
|
|
host:
|
|
- localhost:11434
|
|
method: POST
|
|
parsed_body:
|
|
messages:
|
|
- content: |-
|
|
You are a Recursive Language Model (RLM) agent that solves complex research questions by writing and executing Python code.
|
|
|
|
IMPORTANT: You MUST use the `execute_code` tool to run Python code. The functions described below are ONLY available inside the execute_code tool - you cannot access them any other way. Always execute code to answer questions; do not just describe what code would do.
|
|
|
|
CRITICAL: Inside execute_code, these functions are ALREADY available in the namespace. Do NOT import them - just use them directly:
|
|
- search("query") ✓ CORRECT
|
|
- from haiku.rag import search ✗ WRONG - will fail
|
|
|
|
You have access to a sandboxed Python environment with these haiku.rag functions (use them directly, no imports needed):
|
|
|
|
## Available Functions
|
|
|
|
### search(query, limit=10) -> list[dict]
|
|
Search the knowledge base using hybrid search (vector + full-text).
|
|
Returns list of dicts with keys: chunk_id, content, document_id, document_title, document_uri, score, page_numbers, headings
|
|
|
|
### list_documents(limit=10, offset=0) -> list[dict]
|
|
List available documents in the knowledge base.
|
|
Returns list of dicts with keys: id, title, uri, created_at
|
|
|
|
### get_document(id_or_title) -> str | None
|
|
Get the full text content of a document by ID, title, or URI.
|
|
Returns the document content as a string, or None if not found.
|
|
|
|
### get_docling_document(id_or_title) -> DoclingDocument | None
|
|
Get the structured DoclingDocument object for advanced analysis.
|
|
Returns a DoclingDocument object, or None if not found.
|
|
See "DoclingDocument API" section below for how to use it.
|
|
|
|
### llm(prompt) -> str
|
|
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
|
|
already have the content and just need LLM reasoning.
|
|
|
|
## Pre-loaded Documents Variable
|
|
|
|
If documents were pre-loaded for this session, a `documents` variable is available:
|
|
```python
|
|
# documents is a list of dicts with keys: id, title, uri, content
|
|
for doc in documents:
|
|
print(doc['title'], len(doc['content']))
|
|
```
|
|
Check if it exists with: `if 'documents' in dir(): ...`
|
|
|
|
## Standard Library Modules
|
|
You can import any Python standard library module.
|
|
|
|
## Strategy Guide
|
|
|
|
1. **Explore First**: Start by listing documents or searching to understand what's available. Document names may differ from filenames (e.g., "tbmed593.pdf" might be stored as "TB MED 593" or similar).
|
|
2. **If get_document returns None**: Use `list_documents()` to see actual document titles, or `search()` to find relevant content.
|
|
3. **Iterative Refinement**: Run code, examine results, adjust your approach based on what you find.
|
|
4. **Use print() Liberally**: The REPL captures stdout - print intermediate results to see what you're working with.
|
|
5. **Aggregate with Code**: For counting, averaging, or comparing across documents, write loops and use collections.
|
|
6. **Use llm() for Classification/Extraction**: When you need to classify, summarize, or extract structured data from content you already have, use llm().
|
|
7. **Cite Your Sources**: Track which documents/chunks informed your answer for citation.
|
|
|
|
## DoclingDocument API
|
|
|
|
When you call `get_docling_document(id_or_title)`, you get a DoclingDocument object for structured document analysis.
|
|
|
|
### Properties
|
|
- `doc.texts` - List of all text items (paragraphs, headings, etc.)
|
|
- `doc.tables` - List of all tables
|
|
- `doc.pictures` - List of all pictures/figures
|
|
- `doc.name` - Document name
|
|
|
|
### Methods
|
|
- `doc.iterate_items(with_groups=False)` - Iterate all items with hierarchy level
|
|
Returns tuples of (item, level) where level is nesting depth
|
|
- `doc.export_to_markdown()` - Export entire document as markdown string
|
|
|
|
### Text Item Properties
|
|
- `item.text` - The text content
|
|
- `item.label` - Type: title, paragraph, section_header, list_item, etc. (lowercase enum values)
|
|
- `item.prov` - Provenance (page numbers, bounding boxes)
|
|
|
|
### Table Access
|
|
- `table.data.num_rows`, `table.data.num_cols` - Dimensions
|
|
- `table.data.table_cells` - List of TableCell objects
|
|
- `cell.text`, `cell.start_row_offset_idx`, `cell.start_col_offset_idx`
|
|
|
|
### Example Usage
|
|
```python
|
|
doc = get_docling_document("My Document")
|
|
|
|
# Get all headings
|
|
headings = [t.text for t in doc.texts if "header" in str(t.label)]
|
|
|
|
# Iterate with structure
|
|
for item, level in doc.iterate_items():
|
|
print(" " * level + item.text[:50])
|
|
|
|
# Extract table data
|
|
for table in doc.tables:
|
|
for cell in table.data.table_cells:
|
|
print(f"Row {cell.start_row_offset_idx}, Col {cell.start_col_offset_idx}: {cell.text}")
|
|
```
|
|
|
|
## Example Patterns
|
|
|
|
### Counting documents matching a condition
|
|
```python
|
|
docs = list_documents(limit=100)
|
|
count = 0
|
|
for doc in docs:
|
|
content = get_document(doc['id'])
|
|
if content and 'keyword' in content.lower():
|
|
count += 1
|
|
print(f"Found in: {doc['title']}")
|
|
print(f"Total: {count}")
|
|
```
|
|
|
|
### Aggregating data across documents
|
|
```python
|
|
import re
|
|
numbers = []
|
|
results = search("financial data", limit=20)
|
|
for r in results:
|
|
matches = re.findall(r'\$([\d,]+)', r['content'])
|
|
for m in matches:
|
|
numbers.append(int(m.replace(',', '')))
|
|
print(f"Average: ${sum(numbers)/len(numbers):,.2f}")
|
|
```
|
|
|
|
### Using llm() for classification
|
|
```python
|
|
# Get document content
|
|
content = get_document("Q1 Report")
|
|
# Use llm() to classify sentiment
|
|
sentiment = llm(f"Classify the sentiment as positive, negative, or mixed: {content}")
|
|
print(sentiment)
|
|
```
|
|
|
|
## Workflow
|
|
|
|
1. **ALWAYS start by using execute_code** to explore the knowledge base
|
|
2. Run multiple code blocks as needed to gather information
|
|
3. After collecting data, provide your final answer
|
|
|
|
## Output Format
|
|
|
|
CRITICAL: Your final response MUST be valid JSON matching this exact schema:
|
|
```json
|
|
{"answer": "Your complete answer here as a string", "program": "Your final consolidated program here as a string"}
|
|
```
|
|
|
|
- `answer`: A clear answer to the user's question with key findings and references to specific documents/chunks.
|
|
- `program`: A single, self-contained Python program that produces the answer. Consolidate your exploratory code executions into one clean script.
|
|
|
|
Do NOT return arbitrary JSON structures. Always use the exact format: {"answer": "...", "program": "..."}
|
|
|
|
CRITICAL: You MUST call execute_code at least once before providing your answer. Never give up without trying to execute code first.
|
|
role: system
|
|
- content: What is the total revenue across all quarterly reports?
|
|
role: user
|
|
- content: |-
|
|
<think>
|
|
Need to find quarterly reports, extract revenue amounts, sum. Likely documents titled like "Q1 Report", "Q2 Report"... Let's search "quarterly report revenue".
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"results = search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''],
|
|
r[''page_numbers''], r[''score''])\n"}'
|
|
name: execute_code
|
|
id: call_arzz3ioj
|
|
type: function
|
|
- content: '{"code":"results = search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''],
|
|
r[''page_numbers''], r[''score''])\n","stdout":"3\nQ1 Report [] 0.03226645663380623\nQ2 Report [] 0.03226645663380623\nQ3
|
|
Report [] 0.032258063554763794\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_arzz3ioj
|
|
- content: |-
|
|
<think>
|
|
We have 3 reports. Need to extract revenue. Let's fetch each document content and find revenue. Use regex for "$...".
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"import re\nreports = [''Q1 Report'', ''Q2 Report'', ''Q3 Report'']\nrevenues = {}\nfor rep
|
|
in reports:\n content = get_document(rep)\n if content is None:\n # try by title\n for doc
|
|
in list_documents():\n if rep.lower() in doc[''title''].lower():\n content = get_document(doc[''id''])\n break\n if
|
|
content:\n # find patterns like \"Revenue: $1,234,567\"\n matches = re.findall(r''Revenue[:\\s]*\\$([\\d,]+)'',
|
|
content)\n amounts = [int(m.replace('','','''')) for m in matches]\n if amounts:\n revenues[rep]
|
|
= sum(amounts)\n else:\n revenues[rep] = None\n else:\n revenues[rep] = None\nprint(revenues)\n"}'
|
|
name: execute_code
|
|
id: call_vuqzymvs
|
|
type: function
|
|
- content: '{"code":"import re\nreports = [''Q1 Report'', ''Q2 Report'', ''Q3 Report'']\nrevenues = {}\nfor rep in reports:\n content
|
|
= get_document(rep)\n if content is None:\n # try by title\n for doc in list_documents():\n if
|
|
rep.lower() in doc[''title''].lower():\n content = get_document(doc[''id''])\n break\n if
|
|
content:\n # find patterns like \"Revenue: $1,234,567\"\n matches = re.findall(r''Revenue[:\\s]*\\$([\\d,]+)'',
|
|
content)\n amounts = [int(m.replace('','','''')) for m in matches]\n if amounts:\n revenues[rep]
|
|
= sum(amounts)\n else:\n revenues[rep] = None\n else:\n revenues[rep] = None\nprint(revenues)\n","stdout":"{''Q1
|
|
Report'': None, ''Q2 Report'': None, ''Q3 Report'': None}\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_vuqzymvs
|
|
- content: |2-
|
|
|
|
No content or revenue not matched. Let's try list documents to see actual names and perhaps extract via pages.
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"docs = list_documents(limit=50)\nfor d in docs:\n print(d[''title''])\n"}'
|
|
name: execute_code
|
|
id: call_z0mgsixf
|
|
type: function
|
|
- content: '{"code":"docs = list_documents(limit=50)\nfor d in docs:\n print(d[''title''])\n","stdout":"Q1 Report\nQ2
|
|
Report\nQ3 Report\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_z0mgsixf
|
|
- content: |-
|
|
<think>
|
|
Maybe revenue is in tables. Use docling.
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"doc = get_docling_document(''Q1 Report'')\nprint(doc.name)\n# print headings\nheadings =
|
|
[t.text for t in doc.texts if ''header'' in str(t.label)]\nprint(''headings:'', headlines:=headings[:5])\n#
|
|
find tables\nprint(f\"Tables: {len(doc.tables)}\")\nfor i,table in enumerate(doc.tables):\n print(f\"Table
|
|
{i} rows {table.data.num_rows} cols {table.data.num_cols}\")\n"}'
|
|
name: execute_code
|
|
id: call_acbn2mdz
|
|
type: function
|
|
- content: '{"code":"doc = get_docling_document(''Q1 Report'')\nprint(doc.name)\n# print headings\nheadings = [t.text
|
|
for t in doc.texts if ''header'' in str(t.label)]\nprint(''headings:'', headlines:=headings[:5])\n# find tables\nprint(f\"Tables:
|
|
{len(doc.tables)}\")\nfor i,table in enumerate(doc.tables):\n print(f\"Table {i} rows {table.data.num_rows} cols
|
|
{table.data.num_cols}\")\n","stdout":"content\nheadings: []\nTables: 0\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_acbn2mdz
|
|
- content: |-
|
|
<think>
|
|
No tables. Probably revenue mentioned in paragraphs. Let's fetch entire content and search for "$".
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"content = get_document(''Q1 Report'')\nprint(content[:500])\nprint(''...'')\nprint(content.count(''$''))\n"}'
|
|
name: execute_code
|
|
id: call_y1fiwuj8
|
|
type: function
|
|
- content: '{"code":"content = get_document(''Q1 Report'')\nprint(content[:500])\nprint(''...'')\nprint(content.count(''$''))\n","stdout":"Sales
|
|
report Q1: Revenue was $100,000.\n...\n1\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_y1fiwuj8
|
|
- content: |-
|
|
<think>
|
|
Now extract $ amounts.
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"import re\ncontent = get_document(''Q1 Report'')\namounts = re.findall(r''\\$(\\d{1,3}(?:,\\d{3})*)'',
|
|
content)\nprint(amounts)\nprint([int(a.replace('','','''')) for a in amounts])\n"}'
|
|
name: execute_code
|
|
id: call_i5cijc97
|
|
type: function
|
|
- content: '{"code":"import re\ncontent = get_document(''Q1 Report'')\namounts = re.findall(r''\\$(\\d{1,3}(?:,\\d{3})*)'',
|
|
content)\nprint(amounts)\nprint([int(a.replace('','','''')) for a in amounts])\n","stdout":"[''100,000'']\n[100000]\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_i5cijc97
|
|
model: gpt-oss
|
|
reasoning_effort: low
|
|
stream: false
|
|
tool_choice: auto
|
|
tools:
|
|
- function:
|
|
description: |-
|
|
<summary>Execute Python code in a Docker-sandboxed environment.
|
|
|
|
The code has access to haiku.rag functions (search, list_documents,
|
|
get_document, get_docling_document, llm) and any Python standard
|
|
library module.
|
|
|
|
Use print() to output results.</summary>
|
|
<returns>
|
|
<description>Structured result with success status, stdout, and stderr.</description>
|
|
</returns>
|
|
name: execute_code
|
|
parameters:
|
|
additionalProperties: false
|
|
properties:
|
|
code:
|
|
description: Python code to execute.
|
|
type: string
|
|
required:
|
|
- code
|
|
type: object
|
|
strict: true
|
|
type: function
|
|
- function:
|
|
description: Result from RLM agent execution.
|
|
name: final_result
|
|
parameters:
|
|
additionalProperties: false
|
|
properties:
|
|
answer:
|
|
description: The answer to the user's question
|
|
type: string
|
|
program:
|
|
description: The final consolidated program
|
|
type: string
|
|
required:
|
|
- answer
|
|
- program
|
|
type: object
|
|
strict: true
|
|
type: function
|
|
uri: http://localhost:11434/v1/chat/completions
|
|
response:
|
|
headers:
|
|
content-length:
|
|
- '875'
|
|
content-type:
|
|
- application/json
|
|
parsed_body:
|
|
choices:
|
|
- finish_reason: tool_calls
|
|
index: 0
|
|
message:
|
|
content: ''
|
|
reasoning: Do same for Q2 and Q3.
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"import re\nreports = [''Q1 Report'',''Q2 Report'',''Q3 Report'']\nvalues={}\nfor r in reports:\n c=get_document(r)\n if
|
|
c:\n amounts=re.findall(r''\\$(\\d{1,3}(?:,\\d{3})*)'',c)\n totals=sum(int(a.replace('','',''''))
|
|
for a in amounts)\n values[r]=totals\n else:\n values[r]=None\nprint(values)\nprint(''Total
|
|
revenue:'',sum(v for v in values.values() if v is not None))\n"}'
|
|
name: execute_code
|
|
id: call_4f61ktvo
|
|
index: 0
|
|
type: function
|
|
created: 1770373364
|
|
id: chatcmpl-865
|
|
model: gpt-oss
|
|
object: chat.completion
|
|
system_fingerprint: fp_ollama
|
|
usage:
|
|
completion_tokens: 158
|
|
prompt_tokens: 3239
|
|
total_tokens: 3397
|
|
status:
|
|
code: 200
|
|
message: OK
|
|
- request:
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '15009'
|
|
content-type:
|
|
- application/json
|
|
host:
|
|
- localhost:11434
|
|
method: POST
|
|
parsed_body:
|
|
messages:
|
|
- content: |-
|
|
You are a Recursive Language Model (RLM) agent that solves complex research questions by writing and executing Python code.
|
|
|
|
IMPORTANT: You MUST use the `execute_code` tool to run Python code. The functions described below are ONLY available inside the execute_code tool - you cannot access them any other way. Always execute code to answer questions; do not just describe what code would do.
|
|
|
|
CRITICAL: Inside execute_code, these functions are ALREADY available in the namespace. Do NOT import them - just use them directly:
|
|
- search("query") ✓ CORRECT
|
|
- from haiku.rag import search ✗ WRONG - will fail
|
|
|
|
You have access to a sandboxed Python environment with these haiku.rag functions (use them directly, no imports needed):
|
|
|
|
## Available Functions
|
|
|
|
### search(query, limit=10) -> list[dict]
|
|
Search the knowledge base using hybrid search (vector + full-text).
|
|
Returns list of dicts with keys: chunk_id, content, document_id, document_title, document_uri, score, page_numbers, headings
|
|
|
|
### list_documents(limit=10, offset=0) -> list[dict]
|
|
List available documents in the knowledge base.
|
|
Returns list of dicts with keys: id, title, uri, created_at
|
|
|
|
### get_document(id_or_title) -> str | None
|
|
Get the full text content of a document by ID, title, or URI.
|
|
Returns the document content as a string, or None if not found.
|
|
|
|
### get_docling_document(id_or_title) -> DoclingDocument | None
|
|
Get the structured DoclingDocument object for advanced analysis.
|
|
Returns a DoclingDocument object, or None if not found.
|
|
See "DoclingDocument API" section below for how to use it.
|
|
|
|
### llm(prompt) -> str
|
|
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
|
|
already have the content and just need LLM reasoning.
|
|
|
|
## Pre-loaded Documents Variable
|
|
|
|
If documents were pre-loaded for this session, a `documents` variable is available:
|
|
```python
|
|
# documents is a list of dicts with keys: id, title, uri, content
|
|
for doc in documents:
|
|
print(doc['title'], len(doc['content']))
|
|
```
|
|
Check if it exists with: `if 'documents' in dir(): ...`
|
|
|
|
## Standard Library Modules
|
|
You can import any Python standard library module.
|
|
|
|
## Strategy Guide
|
|
|
|
1. **Explore First**: Start by listing documents or searching to understand what's available. Document names may differ from filenames (e.g., "tbmed593.pdf" might be stored as "TB MED 593" or similar).
|
|
2. **If get_document returns None**: Use `list_documents()` to see actual document titles, or `search()` to find relevant content.
|
|
3. **Iterative Refinement**: Run code, examine results, adjust your approach based on what you find.
|
|
4. **Use print() Liberally**: The REPL captures stdout - print intermediate results to see what you're working with.
|
|
5. **Aggregate with Code**: For counting, averaging, or comparing across documents, write loops and use collections.
|
|
6. **Use llm() for Classification/Extraction**: When you need to classify, summarize, or extract structured data from content you already have, use llm().
|
|
7. **Cite Your Sources**: Track which documents/chunks informed your answer for citation.
|
|
|
|
## DoclingDocument API
|
|
|
|
When you call `get_docling_document(id_or_title)`, you get a DoclingDocument object for structured document analysis.
|
|
|
|
### Properties
|
|
- `doc.texts` - List of all text items (paragraphs, headings, etc.)
|
|
- `doc.tables` - List of all tables
|
|
- `doc.pictures` - List of all pictures/figures
|
|
- `doc.name` - Document name
|
|
|
|
### Methods
|
|
- `doc.iterate_items(with_groups=False)` - Iterate all items with hierarchy level
|
|
Returns tuples of (item, level) where level is nesting depth
|
|
- `doc.export_to_markdown()` - Export entire document as markdown string
|
|
|
|
### Text Item Properties
|
|
- `item.text` - The text content
|
|
- `item.label` - Type: title, paragraph, section_header, list_item, etc. (lowercase enum values)
|
|
- `item.prov` - Provenance (page numbers, bounding boxes)
|
|
|
|
### Table Access
|
|
- `table.data.num_rows`, `table.data.num_cols` - Dimensions
|
|
- `table.data.table_cells` - List of TableCell objects
|
|
- `cell.text`, `cell.start_row_offset_idx`, `cell.start_col_offset_idx`
|
|
|
|
### Example Usage
|
|
```python
|
|
doc = get_docling_document("My Document")
|
|
|
|
# Get all headings
|
|
headings = [t.text for t in doc.texts if "header" in str(t.label)]
|
|
|
|
# Iterate with structure
|
|
for item, level in doc.iterate_items():
|
|
print(" " * level + item.text[:50])
|
|
|
|
# Extract table data
|
|
for table in doc.tables:
|
|
for cell in table.data.table_cells:
|
|
print(f"Row {cell.start_row_offset_idx}, Col {cell.start_col_offset_idx}: {cell.text}")
|
|
```
|
|
|
|
## Example Patterns
|
|
|
|
### Counting documents matching a condition
|
|
```python
|
|
docs = list_documents(limit=100)
|
|
count = 0
|
|
for doc in docs:
|
|
content = get_document(doc['id'])
|
|
if content and 'keyword' in content.lower():
|
|
count += 1
|
|
print(f"Found in: {doc['title']}")
|
|
print(f"Total: {count}")
|
|
```
|
|
|
|
### Aggregating data across documents
|
|
```python
|
|
import re
|
|
numbers = []
|
|
results = search("financial data", limit=20)
|
|
for r in results:
|
|
matches = re.findall(r'\$([\d,]+)', r['content'])
|
|
for m in matches:
|
|
numbers.append(int(m.replace(',', '')))
|
|
print(f"Average: ${sum(numbers)/len(numbers):,.2f}")
|
|
```
|
|
|
|
### Using llm() for classification
|
|
```python
|
|
# Get document content
|
|
content = get_document("Q1 Report")
|
|
# Use llm() to classify sentiment
|
|
sentiment = llm(f"Classify the sentiment as positive, negative, or mixed: {content}")
|
|
print(sentiment)
|
|
```
|
|
|
|
## Workflow
|
|
|
|
1. **ALWAYS start by using execute_code** to explore the knowledge base
|
|
2. Run multiple code blocks as needed to gather information
|
|
3. After collecting data, provide your final answer
|
|
|
|
## Output Format
|
|
|
|
CRITICAL: Your final response MUST be valid JSON matching this exact schema:
|
|
```json
|
|
{"answer": "Your complete answer here as a string", "program": "Your final consolidated program here as a string"}
|
|
```
|
|
|
|
- `answer`: A clear answer to the user's question with key findings and references to specific documents/chunks.
|
|
- `program`: A single, self-contained Python program that produces the answer. Consolidate your exploratory code executions into one clean script.
|
|
|
|
Do NOT return arbitrary JSON structures. Always use the exact format: {"answer": "...", "program": "..."}
|
|
|
|
CRITICAL: You MUST call execute_code at least once before providing your answer. Never give up without trying to execute code first.
|
|
role: system
|
|
- content: What is the total revenue across all quarterly reports?
|
|
role: user
|
|
- content: |-
|
|
<think>
|
|
Need to find quarterly reports, extract revenue amounts, sum. Likely documents titled like "Q1 Report", "Q2 Report"... Let's search "quarterly report revenue".
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"results = search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''],
|
|
r[''page_numbers''], r[''score''])\n"}'
|
|
name: execute_code
|
|
id: call_arzz3ioj
|
|
type: function
|
|
- content: '{"code":"results = search(\"quarterly report revenue\", limit=20)\nprint(len(results))\nfor r in results[:5]:\n print(r[''document_title''],
|
|
r[''page_numbers''], r[''score''])\n","stdout":"3\nQ1 Report [] 0.03226645663380623\nQ2 Report [] 0.03226645663380623\nQ3
|
|
Report [] 0.032258063554763794\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_arzz3ioj
|
|
- content: |-
|
|
<think>
|
|
We have 3 reports. Need to extract revenue. Let's fetch each document content and find revenue. Use regex for "$...".
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"import re\nreports = [''Q1 Report'', ''Q2 Report'', ''Q3 Report'']\nrevenues = {}\nfor rep
|
|
in reports:\n content = get_document(rep)\n if content is None:\n # try by title\n for doc
|
|
in list_documents():\n if rep.lower() in doc[''title''].lower():\n content = get_document(doc[''id''])\n break\n if
|
|
content:\n # find patterns like \"Revenue: $1,234,567\"\n matches = re.findall(r''Revenue[:\\s]*\\$([\\d,]+)'',
|
|
content)\n amounts = [int(m.replace('','','''')) for m in matches]\n if amounts:\n revenues[rep]
|
|
= sum(amounts)\n else:\n revenues[rep] = None\n else:\n revenues[rep] = None\nprint(revenues)\n"}'
|
|
name: execute_code
|
|
id: call_vuqzymvs
|
|
type: function
|
|
- content: '{"code":"import re\nreports = [''Q1 Report'', ''Q2 Report'', ''Q3 Report'']\nrevenues = {}\nfor rep in reports:\n content
|
|
= get_document(rep)\n if content is None:\n # try by title\n for doc in list_documents():\n if
|
|
rep.lower() in doc[''title''].lower():\n content = get_document(doc[''id''])\n break\n if
|
|
content:\n # find patterns like \"Revenue: $1,234,567\"\n matches = re.findall(r''Revenue[:\\s]*\\$([\\d,]+)'',
|
|
content)\n amounts = [int(m.replace('','','''')) for m in matches]\n if amounts:\n revenues[rep]
|
|
= sum(amounts)\n else:\n revenues[rep] = None\n else:\n revenues[rep] = None\nprint(revenues)\n","stdout":"{''Q1
|
|
Report'': None, ''Q2 Report'': None, ''Q3 Report'': None}\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_vuqzymvs
|
|
- content: |2-
|
|
|
|
No content or revenue not matched. Let's try list documents to see actual names and perhaps extract via pages.
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"docs = list_documents(limit=50)\nfor d in docs:\n print(d[''title''])\n"}'
|
|
name: execute_code
|
|
id: call_z0mgsixf
|
|
type: function
|
|
- content: '{"code":"docs = list_documents(limit=50)\nfor d in docs:\n print(d[''title''])\n","stdout":"Q1 Report\nQ2
|
|
Report\nQ3 Report\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_z0mgsixf
|
|
- content: |-
|
|
<think>
|
|
Maybe revenue is in tables. Use docling.
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"doc = get_docling_document(''Q1 Report'')\nprint(doc.name)\n# print headings\nheadings =
|
|
[t.text for t in doc.texts if ''header'' in str(t.label)]\nprint(''headings:'', headlines:=headings[:5])\n#
|
|
find tables\nprint(f\"Tables: {len(doc.tables)}\")\nfor i,table in enumerate(doc.tables):\n print(f\"Table
|
|
{i} rows {table.data.num_rows} cols {table.data.num_cols}\")\n"}'
|
|
name: execute_code
|
|
id: call_acbn2mdz
|
|
type: function
|
|
- content: '{"code":"doc = get_docling_document(''Q1 Report'')\nprint(doc.name)\n# print headings\nheadings = [t.text
|
|
for t in doc.texts if ''header'' in str(t.label)]\nprint(''headings:'', headlines:=headings[:5])\n# find tables\nprint(f\"Tables:
|
|
{len(doc.tables)}\")\nfor i,table in enumerate(doc.tables):\n print(f\"Table {i} rows {table.data.num_rows} cols
|
|
{table.data.num_cols}\")\n","stdout":"content\nheadings: []\nTables: 0\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_acbn2mdz
|
|
- content: |-
|
|
<think>
|
|
No tables. Probably revenue mentioned in paragraphs. Let's fetch entire content and search for "$".
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"content = get_document(''Q1 Report'')\nprint(content[:500])\nprint(''...'')\nprint(content.count(''$''))\n"}'
|
|
name: execute_code
|
|
id: call_y1fiwuj8
|
|
type: function
|
|
- content: '{"code":"content = get_document(''Q1 Report'')\nprint(content[:500])\nprint(''...'')\nprint(content.count(''$''))\n","stdout":"Sales
|
|
report Q1: Revenue was $100,000.\n...\n1\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_y1fiwuj8
|
|
- content: |-
|
|
<think>
|
|
Now extract $ amounts.
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"import re\ncontent = get_document(''Q1 Report'')\namounts = re.findall(r''\\$(\\d{1,3}(?:,\\d{3})*)'',
|
|
content)\nprint(amounts)\nprint([int(a.replace('','','''')) for a in amounts])\n"}'
|
|
name: execute_code
|
|
id: call_i5cijc97
|
|
type: function
|
|
- content: '{"code":"import re\ncontent = get_document(''Q1 Report'')\namounts = re.findall(r''\\$(\\d{1,3}(?:,\\d{3})*)'',
|
|
content)\nprint(amounts)\nprint([int(a.replace('','','''')) for a in amounts])\n","stdout":"[''100,000'']\n[100000]\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_i5cijc97
|
|
- content: |-
|
|
<think>
|
|
Do same for Q2 and Q3.
|
|
</think>
|
|
role: assistant
|
|
tool_calls:
|
|
- function:
|
|
arguments: '{"code":"import re\nreports = [''Q1 Report'',''Q2 Report'',''Q3 Report'']\nvalues={}\nfor r in reports:\n c=get_document(r)\n if
|
|
c:\n amounts=re.findall(r''\\$(\\d{1,3}(?:,\\d{3})*)'',c)\n totals=sum(int(a.replace('','',''''))
|
|
for a in amounts)\n values[r]=totals\n else:\n values[r]=None\nprint(values)\nprint(''Total
|
|
revenue:'',sum(v for v in values.values() if v is not None))\n"}'
|
|
name: execute_code
|
|
id: call_4f61ktvo
|
|
type: function
|
|
- content: '{"code":"import re\nreports = [''Q1 Report'',''Q2 Report'',''Q3 Report'']\nvalues={}\nfor r in reports:\n c=get_document(r)\n if
|
|
c:\n amounts=re.findall(r''\\$(\\d{1,3}(?:,\\d{3})*)'',c)\n totals=sum(int(a.replace('','',''''))
|
|
for a in amounts)\n values[r]=totals\n else:\n values[r]=None\nprint(values)\nprint(''Total revenue:'',sum(v
|
|
for v in values.values() if v is not None))\n","stdout":"{''Q1 Report'': 100000, ''Q2 Report'': 150000, ''Q3 Report'':
|
|
200000}\nTotal revenue: 450000\n","stderr":"","success":true}'
|
|
role: tool
|
|
tool_call_id: call_4f61ktvo
|
|
model: gpt-oss
|
|
reasoning_effort: low
|
|
stream: false
|
|
tool_choice: auto
|
|
tools:
|
|
- function:
|
|
description: |-
|
|
<summary>Execute Python code in a Docker-sandboxed environment.
|
|
|
|
The code has access to haiku.rag functions (search, list_documents,
|
|
get_document, get_docling_document, llm) and any Python standard
|
|
library module.
|
|
|
|
Use print() to output results.</summary>
|
|
<returns>
|
|
<description>Structured result with success status, stdout, and stderr.</description>
|
|
</returns>
|
|
name: execute_code
|
|
parameters:
|
|
additionalProperties: false
|
|
properties:
|
|
code:
|
|
description: Python code to execute.
|
|
type: string
|
|
required:
|
|
- code
|
|
type: object
|
|
strict: true
|
|
type: function
|
|
- function:
|
|
description: Result from RLM agent execution.
|
|
name: final_result
|
|
parameters:
|
|
additionalProperties: false
|
|
properties:
|
|
answer:
|
|
description: The answer to the user's question
|
|
type: string
|
|
program:
|
|
description: The final consolidated program
|
|
type: string
|
|
required:
|
|
- answer
|
|
- program
|
|
type: object
|
|
strict: true
|
|
type: function
|
|
uri: http://localhost:11434/v1/chat/completions
|
|
response:
|
|
headers:
|
|
content-length:
|
|
- '1016'
|
|
content-type:
|
|
- application/json
|
|
parsed_body:
|
|
choices:
|
|
- finish_reason: stop
|
|
index: 0
|
|
message:
|
|
content: '{"answer":"The combined revenue reported across the three quarterly reports equals $450,000. Individual
|
|
figures are:\n• Q1 Report: $100,000\n• Q2 Report: $150,000\n• Q3 Report: $200,000\n\nSources are the full text
|
|
of each report where the amounts are stated in the revenue sentences.","program":"import re\nreports = [''Q1 Report'',''Q2
|
|
Report'',''Q3 Report'']\nvalues={}\nfor r in reports:\n c=get_document(r)\n if c:\n amounts=re.findall(r''\\$(\\d{1,3}(?:,\\d{3})*)'',c)\n totals=sum(int(a.replace('','',''''))
|
|
for a in amounts)\n values[r]=totals\n else:\n values[r]=None\nprint(values)\nprint(''Total revenue:'',sum(v
|
|
for v in values.values() if v is not None))"}'
|
|
role: assistant
|
|
created: 1770373369
|
|
id: chatcmpl-835
|
|
model: gpt-oss
|
|
object: chat.completion
|
|
system_fingerprint: fp_ollama
|
|
usage:
|
|
completion_tokens: 206
|
|
prompt_tokens: 3588
|
|
total_tokens: 3794
|
|
status:
|
|
code: 200
|
|
message: OK
|
|
version: 1
|