Refactored Quantum-API: removed codelama & ollama, added phi endpoint using Ollama

api/endpoints/codelama.py

@@ -1,10 +0,0 @@
-# api/endpoints/codelama.py
-
-from fastapi import APIRouter, HTTPException
-
-router = APIRouter()
-
-@router.post("/")
-async def run_codelama(payload: dict):
-    # Placeholder logic
-    return {"status": "success", "received_input": payload}

api/endpoints/ollama.py

@@ -1,9 +0,0 @@
-from fastapi import APIRouter, Request
-
-router = APIRouter()
-
-@router.post("/")
-async def ollama_response(request: Request):
-    data = await request.json()
-    question = data.get("question", "No question provided.")
-    return {"response": f"Olama received: {question}"}

api/endpoints/phi.py

@@ -0,0 +1,22 @@
+from fastapi import APIRouter, HTTPException
+from pydantic import BaseModel
+import requests
+
+router = APIRouter()
+
+class QueryRequest(BaseModel):
+    query: str
+
+@router.post("/")
+async def phi_response(data: QueryRequest):
+    try:
+        # Call the Ollama local API to generate a response using the phi model
+        response = requests.post(
+            "http://localhost:11434/api/generate",
+            json={"model": "phi:latest", "prompt": data.query, "stream": False}
+        )
+        response.raise_for_status()
+        result = response.json()
+        return {"response": result.get("response", "")}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Phi error: {str(e)}")

api/main.py

@@ -1,8 +1,11 @@
 from fastapi import FastAPI
-from api.endpoints import codelama, ollama
+from api.endpoints import phi
 
-app = FastAPI()
+app = FastAPI(
+    title="Quantum-API",
+    description="Quantum API powered by the Ollama φ (phi) model",
+    version="1.0.0"
+)
 
-# Register routers if you have them
-app.include_router(codelama.router, prefix="/run-codelama")
-app.include_router(ollama.router, prefix="/ollama-response")
+# Mount the phi endpoint at /phi-response/
+app.include_router(phi.router, prefix="/phi-response", tags=["Phi"])

app/app.py

@@ -1,33 +1,21 @@
 import streamlit as st
 import requests
 
-# URL of the FastAPI backend endpoint
-API_URL_OLAMA = "http://localhost:7860/ollama/response"
-API_URL_CODELAMA = "http://localhost:7860/codelama/run"
+# Set the correct URL for the φ endpoint; note that the full path is /phi-response/
+API_URL_PHI = "http://localhost:7860/phi-response/"
 
 def main():
-    st.title("Quantum-API Chat Interface with Olama and CodeLlama")
-
+    st.title("Quantum-API Chat Interface with φ")
     user_input = st.text_input("Ask a question:")
 
     if user_input:
-        if st.button("Chat with Olama"):
-            # Make a POST request to the FastAPI server for Olama
-            response = requests.post(API_URL_OLAMA, json={"question": user_input})
+        if st.button("Chat with φ"):
+            # Send a POST request with the prompt
+            response = requests.post(API_URL_PHI, json={"query": user_input})
             if response.status_code == 200:
-                # Display the response from Olama
-                st.write(f"Olama says: {response.json()['response']}")
+                st.write(f"φ says: {response.json()['response']}")
             else:
-                st.error(f"Error contacting Olama API: {response.status_code}")
+                st.error(f"Error contacting φ API: {response.status_code} - {response.text}")
 
-        if st.button("Run Code with CodeLlama"):
-            # Make a GET request to the FastAPI server for CodeLlama
-            response = requests.get(API_URL_CODELAMA)
-            if response.status_code == 200:
-                # Display the response from CodeLlama
-                st.write(f"CodeLlama result: {response.json()['result']}")
-            else:
-                st.error(f"Error contacting CodeLlama API: {response.status_code}")
-        
 if __name__ == "__main__":
     main()