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

Update docs

Browse source
This commit is contained in:
Yiorgis Gozadinos 2026-03-12 17:55:17 +02:00
parent 2c5128e5ba
commit e8e02f341d
No known key found for this signature in database
2 changed files with 7 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
CHANGELOG.md
View file

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

7
docs/agents/rlm.md
View file

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