7 Commits

Author	SHA1	Message	Date
bolade	17bc5acbc8	Refactor investor similarity search to utilize AI for improved query generation; adjust DataFrame parsing to skip initial rows for better data handling.	2025-09-29 15:58:09 +01:00
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	f2bbcb96f3	Refactor database models and schemas to allow nullable fields; update init_database function for improved initialization.	2025-09-26 15:24:42 +01:00
bolade	0f7beca5e1	made version 2	2025-09-25 17:00:38 +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