Implement manual JSON parsing for company profiles; enhance data extraction and processing efficiency; add comprehensive test script for validation

app/main.py

@@ -47,14 +47,23 @@ async def parse_csv(
     """
     Parse and import CSV data into the database.
 
-    For investors: Expected columns - Name, Website, Final Investor Profile, Final Profile sourcing
-    For companies: Uses legacy LLM-based parsing
-
-    The new investor parser:
+    **For investors:**
+    - Expected columns: Name, Website, Final Investor Profile, Final Profile sourcing
     - Manually parses JSON profiles for efficiency
     - Uses LLM only for currency conversion to USD
     - Handles AUM, fund sizes, and check sizes as integers
-    - Automatically saves to database
+
+    **For companies:**
+    - Expected columns: Name, Website, Investor, Final Investor Profile (company profile)
+    - 100% manual JSON parsing - no LLM needed
+    - Extracts company details, executives, investors, and client categories
+    - Automatically links companies to investors in database
+
+    **Benefits:**
+    - Fast processing (5-10s per record)
+    - Low cost (minimal or no LLM usage)
+    - Accurate data extraction
+    - Automatic database persistence
     """
     # Read uploaded CSV with pandas
     content = await file.read()
@@ -64,15 +73,15 @@ async def parse_csv(
     processor = InvestorProcessor()
 
     if is_investor == 1:
-        # New manual parser with LLM currency conversion
+        # Manual parser with LLM currency conversion
         results = await processor.parse_investors(df, save_to_db=True)
         # Results are already dicts from the new parser
         return results
     else:
-        # Legacy LLM-based company parser
+        # Manual parser for companies (no LLM needed)
         results = await processor.parse_companies(df, save_to_db=True)
-        # Convert Pydantic objects to dictionaries
-        return [r.model_dump() if hasattr(r, "model_dump") else r for r in results]
+        # Results are already dicts from the new parser
+        return results
 
 
 @app.post("/query", response_model=InvestorList, tags=["Querying"])