made querying async

app/db/db.py

@@ -1,5 +1,4 @@
 import os
-from pathlib import Path
 from typing import Annotated
 
 from fastapi import Depends

app/main.py

@@ -1,6 +1,4 @@
 import io
-import logging
-import os
 
 import pandas as pd
 from db.db import Base, db_dependency, engine
@@ -44,6 +42,7 @@ class QueryRequest(BaseModel):
             }
         }
 
+
 class CompanyQueryRequest(BaseModel):
     question: str
 
@@ -54,6 +53,7 @@ class CompanyQueryRequest(BaseModel):
             }
         }
 
+
 @app.get("/")
 def health():
     return {"Hello": "World"}
@@ -122,7 +122,7 @@ async def query_investors(request: QueryRequest):
     - "Healthcare investors in Europe"
     """
     processor = QueryProcessor()
-    results = processor.process_query(request.question)
+    results = await processor.process_query(request.question)
     return results
 
 
@@ -143,7 +143,7 @@ async def query_companies(request: CompanyQueryRequest):
     - "European startups founded after 2019"
     """
     processor = CompanyQueryProcessor()
-    results = processor.process_query(request.question)
+    results = await processor.process_query(request.question)
     return results
 
 

app/services/company_querying.py

@@ -1,3 +1,4 @@
+import asyncio
 import hashlib
 import logging
 import os
@@ -116,11 +117,18 @@ Return ONLY the SQL query, no explanations or markdown.""",
         """Generate cache key from normalized question."""
         return hashlib.md5(question.lower().strip().encode()).hexdigest()
 
-    def process_query(self, question: str) -> PaginatedResponse[CompanyData]:
-        """Process a query by generating and executing SQL directly.
+    # synchronous helper is provided below as `_process_query_sync` and an
+    # async wrapper `process_query` runs it in a thread. This keeps the
+    # FastAPI event loop non-blocking while reusing the existing sync code.
+    async def process_query(self, question: str) -> PaginatedResponse[CompanyData]:
+        """Async wrapper for process_query. Runs blocking work in a thread to avoid
+        blocking the event loop.
+        """
+        return await asyncio.to_thread(self._process_query_sync, question)
 
-        Args:
-            question: The natural language query to process
+    def _process_query_sync(self, question: str) -> PaginatedResponse[CompanyData]:
+        """Synchronous implementation of process_query. This is run in a thread by
+        the async wrapper above.
         """
         cache_key = self._get_cache_key(question)
 

app/services/querying.py

@@ -1,3 +1,4 @@
+import asyncio
 import hashlib
 import logging
 import os
@@ -126,14 +127,19 @@ Return ONLY the SQL query, no explanations or markdown.""",
         """Generate cache key from normalized question."""
         return hashlib.md5(question.lower().strip().encode()).hexdigest()
 
-    def process_query(
+    async def process_query(
         self, question: str, project_id: Optional[int] = None
     ) -> PaginatedResponse[InvestmentResponse]:
-        """Process a query by generating and executing SQL directly.
+        """Async wrapper for process_query. Runs blocking work in a thread to avoid
+        blocking the event loop.
+        """
+        return await asyncio.to_thread(self._process_query_sync, question, project_id)
 
-        Args:
-            question: The natural language query to process
-            project_id: Optional project ID for compatibility scoring
+    def _process_query_sync(
+        self, question: str, project_id: Optional[int] = None
+    ) -> PaginatedResponse[InvestmentResponse]:
+        """Synchronous implementation of process_query. This is run in a thread by
+        the async wrapper above.
         """
         cache_key = self._get_cache_key(question)