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.

app/services/querying.py

@@ -0,0 +1,61 @@
+from typing import Optional
+
+import chromadb
+from langchain_openai import ChatOpenAI
+from pydantic_schemas import Investor, InvestorList
+from settings import settings
+
+# Add these imports for your databases
+# from sqlalchemy.ext.asyncio import AsyncSession
+# from your_vector_db import VectorDBClient
+
+
+class QueryProcessor:
+    def __init__(
+        self,
+        sql_session: Optional[object] = None,
+        vector_db_client: Optional[object] = None,
+    ):
+        self.llm = ChatOpenAI(
+            api_key=settings.OPENROUTER_API_KEY,
+            base_url="https://openrouter.ai/api/v1",
+            model="openai/gpt-oss-120b:free",
+            temperature=0,
+        )
+
+        self.structured_llm = self.llm.with_structured_output(InvestorList)
+        self.sql_session = sql_session
+        self.vector_db_client = vector_db_client
+
+        self.vector_db_client = chromadb.PersistentClient(path="./chroma_db")
+        self.collection = self.vector_db_client.get_or_create_collection(
+            name="investor_descriptions",
+            metadata={
+                "description": "Investor descriptions and investment thesis focus"
+            },
+        )
+
+    def query_sql_database(self, query: str) -> Optional[InvestorList]:
+        """Query the SQL database for investor information."""
+        if not self.sql_session:
+            return None
+
+        # Implement SQL querying logic here
+        result = self.sql_session.execute(query)
+        investors = result.scalars().all()
+        return InvestorList(investors=investors)
+
+    def query_vector_database(self, query: str) -> Optional[InvestorList]:
+        """Query the vector database for investor information."""
+        if not self.vector_db_client:
+            return None
+
+        # Implement vector database querying logic here
+        results = self.vector_db_client.query(collection=self.collection, query=query)
+        investors = [Investor(**doc.metadata) for doc in results.documents]
+        return InvestorList(investors=investors)
+
+    def process_query(self, question: str) -> InvestorList:
+        """Process a query using the LLM and return structured investor data."""
+        response = self.structured_llm.predict(question=question)
+        return response