Feat/agent knowledge graph tool#15
Merged
Merged
Conversation
This commit introduces a major new capability to the agentic system by adding a KnowledgeGraphTool. This tool allows the agent to query a Neo4j database, enabling it to answer complex, relational questions that are impossible for a standard RAG pipeline to handle. Key changes include: - Created a class with a Text-to-Cypher module powered by . - Engineered a robust prompt with schema, rules, and few-shot examples to guide the LLM's query generation. - Implemented a Pydantic schema for tool inputs to ensure reliable argument passing from the manager agent. - Upgraded the agent's prompt to enable intelligent routing between the RAG tool and the new Knowledge Graph tool. - Added a entry point for running the agent and systematically tested all reasoning paths. - Refactored the core agent logic to manage secrets via a file and to ensure explicit API key configuration for all LLM clients.
This commit introduces a major new capability to the agentic system by adding a KnowledgeGraphTool. This tool allows the agent to query a Neo4j database, enabling it to answer complex, relational questions that are impossible for a standard RAG pipeline to handle. Key changes include: - Created a class with a Text-to-Cypher module powered by . - Engineered a robust prompt with schema, rules, and few-shot examples to guide the LLM's query generation. - Implemented a Pydantic schema for tool inputs to ensure reliable argument passing from the manager agent. - Upgraded the agent's prompt to enable intelligent routing between the RAG tool and the new Knowledge Graph tool. - Added a entry point for running the agent and systematically tested all reasoning paths. - Refactored the core agent logic to manage secrets via a file and to ensure explicit API key configuration for all LLM clients.
This commit introduces a major new capability to the agentic system by adding a KnowledgeGraphTool. This tool allows the agent to query a Neo4j database, enabling it to answer complex, relational questions that are impossible for a standard RAG pipeline to handle. Key changes include: - Created a class with a Text-to-Cypher module powered by . - Engineered a robust prompt with schema, rules, and few-shot examples to guide the LLM's query generation. - Implemented a Pydantic schema for tool inputs to ensure reliable argument passing from the manager agent. - Upgraded the agent's prompt to enable intelligent routing between the RAG tool and the new Knowledge Graph tool. - Added a entry point for running the agent and systematically tested all reasoning paths. - Refactored the core agent logic to manage secrets via a file and to ensure explicit API key configuration for all LLM clients.
This commit introduces a major new capability to the agentic system by adding a KnowledgeGraphTool. This tool allows the agent to query a Neo4j database, enabling it to answer complex, relational questions that are impossible for a standard RAG pipeline to handle. Key changes include: - Created a class with a Text-to-Cypher module powered by . - Engineered a robust prompt with schema, rules, and few-shot examples to guide the LLM's query generation. - Implemented a Pydantic schema for tool inputs to ensure reliable argument passing from the manager agent. - Upgraded the agent's prompt to enable intelligent routing between the RAG tool and the new Knowledge Graph tool. - Added a entry point for running the agent and systematically tested all reasoning paths. - Refactored the core agent logic to manage secrets via a file and to ensure explicit API key configuration for all LLM clients.
This commit introduces a major new capability to the agentic system by adding a KnowledgeGraphTool. This tool allows the agent to query a Neo4j database, enabling it to answer complex, relational questions that are impossible for a standard RAG pipeline to handle. Key changes include: - Created a class with a Text-to-Cypher module powered by . - Engineered a robust prompt with schema, rules, and few-shot examples to guide the LLM's query generation. - Implemented a Pydantic schema for tool inputs to ensure reliable argument passing from the manager agent. - Upgraded the agent's prompt to enable intelligent routing between the RAG tool and the new Knowledge Graph tool. - Added a entry point for running the agent and systematically tested all reasoning paths. - Refactored the core agent logic to manage secrets via a file and to ensure explicit API key configuration for all LLM clients.
This commit introduces a major new capability to the agentic system by adding a KnowledgeGraphTool. This tool allows the agent to query a Neo4j database, enabling it to answer complex, relational questions that are impossible for a standard RAG pipeline to handle. Key changes include: - Created a class with a Text-to-Cypher module powered by . - Engineered a robust prompt with schema, rules, and few-shot examples to guide the LLM's query generation. - Implemented a Pydantic schema for tool inputs to ensure reliable argument passing from the manager agent. - Upgraded the agent's prompt to enable intelligent routing between the RAG tool and the new Knowledge Graph tool. - Added a entry point for running the agent and systematically tested all reasoning paths. - Refactored the core agent logic to manage secrets via a file and to ensure explicit API key configuration for all LLM clients.
This commit introduces a major new capability to the agentic system by adding a KnowledgeGraphTool. This tool allows the agent to query a Neo4j database, enabling it to answer complex, relational questions that are impossible for a standard RAG pipeline to handle. Key changes include: - Created a class with a Text-to-Cypher module powered by . - Engineered a robust prompt with schema, rules, and few-shot examples to guide the LLM's query generation. - Implemented a Pydantic schema for tool inputs to ensure reliable argument passing from the manager agent. - Upgraded the agent's prompt to enable intelligent routing between the RAG tool and the new Knowledge Graph tool. - Added a entry point for running the agent and systematically tested all reasoning paths. - Refactored the core agent logic to manage secrets via a file and to ensure explicit API key configuration for all LLM clients.
Refactored the settings management to use a 'lazy' function-based approach () instead of an 'eager' global constant. This was necessary to resolve a persistent in the pytest environment where tests were failing during collection. The eager check for the API key was preventing any tests from running without credentials. This change decouples the application modules from the need for a globally available API key, making the entire system more modular and testable.
Added a patch to mock the get_google_api_key function. This fully isolates the unit test from needing real credentials, resolving the final test failure in the CI environment.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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.
No description provided.