Big update #22
Merged
Big update #22
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
…view and final steps
… - Replace create_batch_document_translation_job with create_job API - Update input/output location models - Add proper model metadata configuration - Update job monitoring - Add better timestamp handling - Remove unused functions - Improve error handling
… version to 2.141.1 - Add yaml dependency for config parsing
… service config - Set source and target bucket names - Configure language codes
…nglish sentences - Keep under character limits - Total text under batch limit
…ket content listing - Add timing metrics and progress tracking - Improve error handling and status display - Add visual formatting and symbols - Add job statistics and success rate
… ChromaDB, FastAPI, and transformers dependencies
…ssor class for document processing - Add support for single file and directory processing - Add command-line interface for PDF processing - Implement metadata extraction and chunking
…lass for document storage - Add support for PDF and general knowledge collections - Add command-line interface for store management - Implement document querying with similarity search
…OpenAI-based RAG agent with GPT-4 - Add local RAG agent with Mistral-7B - Implement query analysis and routing - Add command-line interface for both agents
…ment upload and querying - Add CORS middleware for cross-origin requests - Implement file upload handling and cleanup - Add error handling and validation
…r Twitter/X and GitHub URLs - Improve error messages with detailed explanations - Add content type metadata for better filtering
…o generated files - Exclude embeddings and database files - Ignore generatedJSON outputs
…d setup instructions - Add usage examples for all components - Add Chain of Thought documentation - Update API endpoints section
… CUDA compilation warning suppression - Reduce initial chunk size from 384 to 256 tokens - Add fallback mechanism - Suppress token length warnings - Improve chunking error handling
…ment_id for each PDF - Add document_id to chunk metadata - Update return values to include document_id - Update all methods to handle new return format
…andle docuent_id correctly - Update FastAPI endpoint to use returned document_id - Fix document_id handling in vector store integration
…atbot message format to use list of pairs - Update return type annotation - Maintain chat history correctly
…for GitHub repositories - Update VectorStore with repository collection - Enhance RAG agents to use repository context - Fix language selection in Gradio app
…h string summary handling - Add type checking for file content - Improve output formatting with emojis and stats
…ic querying - Add repo processing to Gradio, add collection-specific querying, simplify metadata, improve chunking
- Add specialized agents (Planner, Research, Reasoning, Synthesis) - Modify RAG and LocalRAG agents to use multi-agent CoT - Add test file for multi-agent system - Update README with new CoT documentation - Make local model the default option
- Add multi-agent CoT system integration - Add detailed console logging - Improve response formatting with emojis - Show reasoning steps, final answer, and sources
- Add checks for researcher agent availability - Handle cases with no context available - Provide fallback to general knowledge - Fix NoneType error in CoT processing
- Add consistent error handling for missing agents in both RAG implementations - Add fallback to general response when agents are unavailable - Improve logging for agent availability and errors - Ensure graceful degradation in Chain of Thought processing
- Remove global agent initiaization with use_cot - Create new agent instance per request with correct CoT setting - Add better error messages for missing configurations
- Add llm field to base Agent class - Add vector_store field to ResearchAgent - Fix initialization of agent fields through super().__init__
- Suppress tokenizer warnings - Ad detailed logging for all agent operations - Add visual separators and emojis for better log readability - Log all prompts and responses with proper formatting
- Split chat interface into Standard and Chain of Thought tabs - Add send buttons to both chat interfaces - Update instructions with detailed explanations - Improve layout with better scaling for input fields
- Make agent prompts more concise and focused - Add real-time step conclusions in chat interface - Show intermediate reasoning steps in Gradio - Improve prompt efficiency for faster responses
Major enhancements: - Add multi-agent Chain of Thought reasoning with specialized agents (Planner, Researcher, Reasoner, Synthesizer) - Add support for both Oracle DB 23ai and local LLM (Ollama) deployments - Implement containerized deployment with Podman for Windows/Mac/Linux - Add comprehensive logging and error handling - Add real-time step-by-step reasoning visualization - Improve documentation with deployment guides and troubleshooting - Add support for multiple container configurations Technical improvements: - Optimize agent prompts for faster responses - Add proper error handling for database connections - Add HuggingFace embeddings error recovery - Improve container networking and initialization
oracle-contributor-agreement
bot
added
the
OCA Verified
paulparkinson
approved these changes
Feb 24, 2025
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.
No description provided.