feat: add Airweave tool integration with advanced search features #20111
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Add AirweaveToolSpec with 5 tool functions: * search_collection: Simple search with default settings * advanced_search_collection: Full control over retrieval parameters * search_and_generate_answer: RAG-style direct answers * list_collections: Discover available collections * get_collection_info: Get collection details - Advanced search features: * Multiple retrieval strategies (hybrid, neural, keyword) * Temporal relevance weighting for recent content * Query expansion for better recall * Auto-interpret filters from natural language * LLM-based reranking for improved relevance * Natural language answer generation - 13 passing unit tests with comprehensive coverage - Full documentation with usage examples - Jupyter notebook example demonstrating all features - Follows LlamaIndex conventions (gpt-4o-mini, async patterns) - Compatible with FunctionAgent - Production tested with real data
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
dosubot
bot
added
the
size:XL
AstraBert
reviewed
Oct 20, 2025
| framework_version: Framework version for analytics | ||
|
|
||
| """ | ||
| from airweave import AirweaveSDK |
There was a problem hiding this comment.
Can we place imports at the top? :)
| List of Document objects containing search results with metadata | ||
|
|
||
| """ | ||
| from airweave import SearchRequest |
Comment on lines
+205
to
+207
| else: | ||
| # Fallback if no answer generated | ||
| return "No answer could be generated from the search results." |
There was a problem hiding this comment.
raise an error? or a warning maybe? I would personally be in favor of doing:
Suggested change
| else: | |
| # Fallback if no answer generated | |
| return "No answer could be generated from the search results." | |
| else: | |
| # Fallback if no answer generated | |
| warnings.warn("No answer could be generated from the search results", UserWarning) | |
| return None |
And then type the return type of the function as: Optional[str] so that the user knows, when the result is None, that no answer was generated
There was a problem hiding this comment.
(this means importing also warnings at the top)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR adds Airweave as a tool integration, enabling LlamaIndex agents to search across data automatically synced from 30+ sources.
What is Airweave?
Airweave is an open-source platform that syncs data from multiple sources (Google Drive, Notion, GitHub, databases, APIs, etc.) and provides unified search with advanced retrieval capabilities.
Implementation:
AirweaveToolSpec with 5 tool functions:
search_collection: Simple search with default settingsadvanced_search_collection: Full control over retrieval parameterssearch_and_generate_answer: RAG-style direct answerslist_collections: Discover available collectionsget_collection_info: Get collection detailsAdvanced search features:
Testing & Documentation:
Links:
Fixes #20110
New Package?
Did I fill in the
tool.llamahubsection in thepyproject.tomland provide a detailed README.md for my new integration or package?Version Bump?
Did I bump the version in the
pyproject.tomlfile of the package I am updating? (Except for thellama-index-corepackage)Type of Change
Please delete options that are not relevant.
[x] New feature (non-breaking change which adds functionality)
How Has This Been Tested?
Testing details:
All tests use mocked Airweave SDK calls and cover:
Additionally tested with production Airweave instance and real data.
Suggested Checklist:
uv run make format; uv run make lintto appease the lint gods