feat: Enhance backend with context management, error handling, and refactored code #4286
Conversation
This file contains 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
dosubot
bot
added
size:XXL
…and context management - Introduced `AgentActionRouter` to route agent flow based on action type. - Added `DecideActionComponent` for determining actions from context and prompts. - Implemented `ExecuteActionComponent` to execute actions using available tools. - Created `GenerateThoughtComponent` for generating thoughts based on context. - Developed `ProvideFinalAnswerComponent` to generate final answers from context. - Built `AgentContextBuilder` for constructing `AgentContext` instances. - Added `ObserveResultComponent` to process and observe action results. - Implemented `CheckTerminationComponent` to determine if the agent should continue or terminate.
…tion - Introduced `AgentContext` class in `context.py` to handle agent state, including tools, language model, and context history. - Implemented serialization methods for converting agent context to JSON-compatible format. - Added validation for language model instances to ensure compatibility. - Provided methods for updating and retrieving full context, including context history management.
- Introduced a `_ctx` attribute to store context data. - Added `ctx` property to access the graph's context, raising an error if the graph is not built. - Implemented `add_to_ctx` method to add key-value pairs to the context with an optional overwrite flag. - Implemented `update_ctx` method to update the context with a dictionary of values, ensuring the graph is built and the input is a dictionary.
…sing to use async iteration.
…nent structure - Removed "BaseTool" from input types for "ToolCallingAgent" to streamline tool handling. - Updated agent component to a more modular structure with new prompts and input configurations. - Replaced deprecated methods and fields with updated implementations for improved functionality. - Adjusted metadata and configuration settings for better clarity and usability.
- Added `Agent` import to `__init__.py` for better module accessibility. - Improved error handling in `aiml_embeddings.py` by raising a `ValueError` when the expected embedding count is not met. - Cleaned up redundant imports in `test_cycles.py` to enhance code readability.
ogabrielluiz
force-pushed
the
feat-context
branch
from
a547195
to
d5f03a2
Compare
github-actions
bot
added
enhancement
…ogic - Replaced complex agent flow with a simplified guessing game using OpenAI components and conditional routing. - Introduced `TextInputComponent` and updated `ChatInput` initialization. - Added new test `test_conditional_router_max_iterations` to validate conditional routing with max iterations. - Updated graph cyclicity assertions and snapshot checks for improved test coverage. - Removed deprecated agent components and related logic.
…erate_and_stop_once method
dosubot
bot
added
size:L
ogabrielluiz
changed the title
github-actions
bot
added
enhancement
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.
This pull request includes significant updates to the backend, focusing on enhancing context management, improving error handling, and refactoring code for better maintainability. The most important changes include the introduction of the
AgentContextclass, updates to theComponentclass for context handling, and various improvements to the graph and tracing services.Check the added test for an example use case of the context.
Context Management Enhancements:
src/backend/base/langflow/base/agents/context.py: Introduced theAgentContextclass to manage agent context, including serialization and validation of language models.src/backend/base/langflow/custom/custom_component/component.py: Added methods to theComponentclass for managing context, includingadd_to_ctx,update_ctx, and_pre_run_setup. [1] [2] [3]Error Handling Improvements:
src/backend/base/langflow/base/embeddings/aiml_embeddings.py: Enhanced error messages inembed_documentsto provide more detailed information.Code Refactoring:
src/backend/base/langflow/components/embeddings/aiml.py: Refactored imports to use the new module structure forAIMLEmbeddingsImpl.src/backend/base/langflow/components/embeddings/util/__init__.py: Removed redundant import forAIMLEmbeddingsImpl.Graph Improvements:
src/backend/base/langflow/graph/graph/base.py: Added context handling to theGraphclass and improved cycle detection logic. [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11]src/backend/base/langflow/graph/graph/runnable_vertices_manager.py: Added support for managing vertices in cycles. [1] [2] [3]Tracing Service Updates:
src/backend/base/langflow/services/tracing/langsmith.py: Improved tracing service to handle scenarios where the run tree is not ready. [1] [2] [3]