bolade/Anton_wireframe
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
15 Commits 3 Branches 0 Tags
6d902345c0cf5a7a18575b47914b9f21e0cde5cc
Commit Graph

8 Commits

Author SHA1 Message Date
bolade 6d902345c0 Refactor investor and company schemas to allow optional fields; update filtering logic in read_companies function and add find_similar_investors endpoint; change LLM model in InvestorProcessor and QueryProcessor for improved performance. 2025-09-27 10:45:08 +01:00
bolade d36367fbe9 Add project management functionality with CRUD operations and associations; introduce project schemas and update main application routing. 2025-09-27 08:53:59 +01:00
bolade abac19c6ae Update .gitignore to exclude __pycache__ directories and modify schemas to allow optional fields for better flexibility; adjust batch size in InvestorProcessor for improved processing efficiency. 2025-09-26 15:56:29 +01:00
bolade 0f7beca5e1 made version 2 2025-09-25 17:00:38 +01:00
bolade 29d9292cbd Fix database URL in db.py and update import path for schemas in llm_parser.py 2025-09-11 15:46:39 +01:00
bolade ba0ed169ce Implement investor processing and querying functionality 
- Added InvestorProcessor class for processing CSV data in batches and saving to SQL and vector databases.
- Introduced QueryProcessor class for querying investor information from SQL and vector databases.
- Integrated OpenAI's ChatGPT for structured output generation.
- Implemented data cleaning and control character removal in CSV processing.
- Added asynchronous processing capabilities for batch handling.
- Established connection to ChromaDB for vector storage of investor descriptions.
- Defined structured output schemas using Pydantic for investor data validation.
- Enhanced settings management for API key and database configurations.
 2025-08-29 18:42:55 +01:00
bolade 4c99638d94 Remove deprecated demo, ingest, schema, and test parser files; add new LLM parser implementation and settings configuration 2025-08-28 23:09:14 +01:00
bolade bbf6af58f0 Implement LLM-powered Investor Parser with CSV processing, SQL and vector database integration 
- Added FastAPI application with a simple root endpoint.
- Developed LLMInvestorParser class for processing investor data from CSV files.
- Integrated OpenAI API for LLM enhancements and JSON cleaning.
- Implemented structured data extraction and saving to SQL database.
- Added functionality to save investor descriptions to ChromaDB for vector similarity search.
- Created command-line interface for processing files and searching investors.
- Added schema definitions for Investor and related data models using SQLAlchemy and Pydantic.
- Implemented logging for better traceability and error handling.
- Included requirements.txt for dependency management.
 2025-08-28 22:51:58 +01:00