- Updated FundTable to replace JSON fields for investment stages and sectors with relationships.
- Introduced InvestmentStageTable and fund_investment_stages association table.
- Created fund_sectors association table for many-to-many relationship with sectors.
- Changed geographic_focus from JSON array to a simple string.
- Migrated existing data to new schema, ensuring data integrity and normalization.
- Updated related schemas, routers, and services to reflect new structure.
- Added migration script to handle data transformation and schema updates.
- Implemented tests to verify new relationships and data integrity.
- Removed deprecated `stage_focus` column from `InvestorTable` and `InvestorSchema`.
- Updated `FundTable` to change `fund_size` from VARCHAR to INTEGER and added `check_size_lower` and `check_size_upper` columns.
- Modified API routes to return investor-fund combinations as separate entries.
- Created new `InvestorFundData` schema for combined investor-fund responses.
- Implemented LLM parsing for check size range from estimated investment size.
- Updated database migration script to reflect schema changes and ensure data integrity.
- Removed obsolete verification and test scripts related to the old schema.
- Implemented a new test script `test_parser.py` to validate the functionality of the manual JSON parser.
- The script loads investor data from a CSV file and processes a sample of three investors.
- Results include detailed information about each investor, their funds, team members, and investment thesis.
- Added error handling for missing API key in the environment variables.
- 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.
- 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.
bolade