feat: remove cache

README.md

@@ -11,11 +11,9 @@ Live at https://tenantfirstaid.com/
 
 ### Prerequisites
  - [uv](https://docs.astral.sh/uv/getting-started/installation/)
- - [docker](https://www.docker.com/)
 
 1. copy `backend/.env.example` to a new file named `.env` in the same directory and populate it with your `OPENAI_API_KEY`. You can set an invalid key, in which case the bot will return error messages. This may still be useful for developing other features.
 1. `cd backend`
-1. `docker-compose up` (use `-d` if you want to run this in the background, otherwise open a new terminal)
 1. `uv sync`
 1. If you have not uploaded the Oregon Housing Law documents to a vector store in OpenAI, run `uv run scripts/create_vector_store.py` and follow the instructions to add the vector store ID to your `.env`.
 1. `uv run python -m tenantfirstaid.app`

backend/.env.example

@@ -1,14 +1,8 @@
 # Specify a different model
-MODEL_NAME=gpt-2.5-flash
+MODEL_NAME=gpt-2.5-pro
 
-# Vector store ID for OpenAI (use the create_vector_store script to create one)
-VECTOR_STORE_ID=my_vector_store_id
-
-# DB Info
-DB_HOST=127.0.0.1
-DB_PORT=6379
-DB_USE_SSL=false
+# Specify model for eval user
+USER_MODEL_NAME=gemini-2.0-flash-lite
 
-# Not used for local dev
-#DB_USERNAME=default
-#DB_PASSWORD=password
+# Vector store ID for OpenAI (use the create_vector_store script to create one)
+GEMINI_RAG_CORPUS=my_vector_store_id

backend/pyproject.toml

@@ -4,7 +4,6 @@ version = "0.2.0"
 requires-python = ">=3.12"
 dependencies = [
   "flask>=3.1.1",
-  "valkey>=6.1.0",
   "gunicorn>=23.0.0",
   "google-auth>=2.40.3",
   "google-genai>=1.28.0",

backend/tenantfirstaid/app.py

@@ -1,8 +1,5 @@
 from pathlib import Path
-from flask import Flask, jsonify, session
-import os
-import secrets
-
+from flask import Flask
 
 if Path(".env").exists():
     from dotenv import load_dotenv
@@ -11,46 +8,10 @@
 
 from .chat import ChatView
 
-from .session import InitSessionView, TenantSession
-from .citations import get_citation
-
 app = Flask(__name__)
 
-# Configure Flask sessions
-app.secret_key = os.getenv("FLASK_SECRET_KEY", secrets.token_hex(32))
-app.config["SESSION_COOKIE_HTTPONLY"] = True
-app.config["SESSION_COOKIE_SECURE"] = os.getenv("ENV", "dev") == "prod"
-app.config["SESSION_COOKIE_SAMESITE"] = "Lax"
-
-
-tenant_session = TenantSession()
-
-
-@app.get("/api/history")
-def history():
-    saved_session = tenant_session.get()
-    return jsonify(saved_session["messages"])
-
-
-@app.post("/api/clear-session")
-def clear_session():
-    session.clear()
-    return jsonify({"success": True})
-
-
-app.add_url_rule(
-    "/api/init",
-    view_func=InitSessionView.as_view("init", tenant_session),
-    methods=["POST"],
-)
-
-app.add_url_rule(
-    "/api/query", view_func=ChatView.as_view("chat", tenant_session), methods=["POST"]
-)
 
-app.add_url_rule(
-    "/api/citation", endpoint="citation", view_func=get_citation, methods=["GET"]
-)
+app.add_url_rule("/api/query", view_func=ChatView.as_view("chat"), methods=["POST"])
 
 if __name__ == "__main__":
     app.run(debug=True, host="0.0.0.0", port=5001)

backend/tenantfirstaid/chat.py

@@ -74,6 +74,7 @@ def generate_gemini_chat_response(
         instructions=None,
         model_name=MODEL,
     ):
+        print(f"Generating response for messages: {messages}")
         instructions = (
             instructions
             if instructions
@@ -112,28 +113,26 @@ def generate_gemini_chat_response(
             generation_config=GenerationConfig(temperature=0.2),
             tools=[rag_retrieval_tool] if use_tools else None,
         )
+        print(f"Response: {response}")
 
         return response
 
 
 class ChatView(View):
-    def __init__(self, tenant_session) -> None:
-        self.tenant_session = tenant_session
+    def __init__(self) -> None:
         self.chat_manager = ChatManager()
 
     def dispatch_request(self, *args, **kwargs) -> Response:
         data = request.json
-        user_msg = data["message"]
-
-        current_session = self.tenant_session.get()
-        current_session["messages"].append(dict(role="user", content=user_msg))
+        messages = data["messages"]
+        print(f"Received messages: {messages}")
 
         def generate():
             # Use the new Responses API with streaming
             response_stream = self.chat_manager.generate_gemini_chat_response(
-                current_session["messages"],
-                current_session["city"],
-                current_session["state"],
+                messages,
+                data["city"],
+                data["state"],
                 stream=True,
             )
 
@@ -142,15 +141,6 @@ def generate():
                 assistant_chunks.append(event.candidates[0].content.parts[0].text)
                 yield event.candidates[0].content.parts[0].text
 
-            # Join the complete response
-            assistant_msg = "".join(assistant_chunks)
-
-            current_session["messages"].append(
-                {"role": "model", "content": assistant_msg}
-            )
-
-            self.tenant_session.set(current_session)
-
         return Response(
             stream_with_context(generate()),
             mimetype="text/plain",