Feat/support deep research #567
Closed
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
…kflow This commit adds a comprehensive deep research skill that: - Supports multi-stage research with dynamic topic exploration - Implements structured search, extraction, and analysis processes - Provides detailed research synthesis and progress tracking - Includes modular research prompts and activity logging - Handles time-limited research with error resilience The new DeepResearch skill enables systematic and adaptive research across various topics.
This commit introduces a new content extraction feature with several key improvements: - Added `extract` method to RAG service for flexible content retrieval - Implemented HTML to markdown conversion and markdown cleaning utilities - Updated skill service to support content extraction workflow - Enhanced OpenAPI schema with extraction request and response types - Improved content processing with topic-focused extraction and length limiting The new extraction capabilities enable more precise and context-aware content retrieval across different sources.
This commit moves the research-related Zod schemas from the deep-research skill file to a new dedicated schema module, improving code organization and reusability. The changes include: - Created a new `schema.ts` file in the deep-research module - Moved existing research-related schemas (titleSchema, searchResultSchema, etc.) to the new file - Updated imports in the deep-research skill to use the new schema module - Maintained existing schema definitions and descriptions
…ling This commit improves the deep research skill's robustness and tracking capabilities by: - Adding a class-level research state property for better tracking - Implementing more detailed activity logging for search and analysis stages - Introducing advanced error handling with retry mechanisms - Adding support for optional URL-specific search - Enhancing source tracking and progress reporting - Cleaning up research state after completion or failure
This commit fixes import paths for LangChain message types, replacing '@langchain/core/dist/messages' with '@langchain/core/messages' in several skill-related files. The changes ensure consistent and correct imports across the project.
… activity tracking
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Summary
Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.
Tip
Close issue syntax:
Fixes #<issue number>orResolves #<issue number>, see documentation for more details.Impact Areas
Please check the areas this PR affects:
Screenshots/Videos
Checklist
Important
Please review the checklist below before submitting your pull request.
dev/reformat(backend) andcd web && npx lint-staged(frontend) to appease the lint gods