first commit

.gitignore

@@ -0,0 +1,12 @@
+# .gitignore
+__pycache__/
+*.py[cod]
+*$py.class
+.env
+.env.local
+venv/
+.idea/
+.vscode/
+*.log
+data/*
+!data/.gitkeep

README.md

@@ -5,6 +5,59 @@ colorFrom: gray
 colorTo: yellow
 sdk: docker
 pinned: false
+port: 7860
+app_port: 7860
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Pet Assistant LlamaIndex API
+
+This API provides a chat endpoint powered by LlamaIndex, specifically designed to assist with pet-related queries. The service is compatible with Hugging Face's Chat UI and exposes a REST API on port 7860.
+
+## API Endpoints
+
+### Chat Endpoint
+
+```http
+POST /chat
+Content-Type: application/json
+```
+
+Request body:
+```json
+{
+    "messages": [
+        {
+            "role": "user",
+            "content": "How often should I feed my cat?"
+        }
+    ],
+    "temperature": 0.7,
+    "max_tokens": 1024,
+    "parameters": {}
+}
+```
+
+Response:
+```json
+{
+    "content": "The response from LlamaIndex...",
+    "stop": null,
+    "usage": {
+        "prompt_tokens": 0,
+        "completion_tokens": 0,
+        "total_tokens": 0
+    }
+}
+```
+
+### Health Check
+
+```http
+GET /health
+```
+
+Response:
+```json
+{
+    "status": "healthy"
+}

app.py

@@ -0,0 +1,114 @@
+# app.py
+from fastapi import FastAPI, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+from typing import List, Dict, Optional, Union
+import os
+from llama_index import VectorStoreIndex, SimpleDirectoryReader, ServiceContext
+from llama_index.llms import OpenAI
+import logging
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+app = FastAPI()
+
+# Configure CORS
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # Adjust this in production
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+class ChatMessage(BaseModel):
+    role: str
+    content: str
+
+class ChatRequest(BaseModel):
+    messages: List[ChatMessage]
+    temperature: Optional[float] = 0.7
+    max_tokens: Optional[int] = 1024
+    parameters: Optional[Dict] = {}
+
+class ChatResponse(BaseModel):
+    content: str
+    stop: Optional[List[str]] = None
+    usage: Dict[str, int]
+
+# Initialize LlamaIndex components
+@app.on_event("startup")
+async def startup_event():
+    try:
+        # Initialize OpenAI client (can be replaced with other LLM providers)
+        llm = OpenAI(
+            model="gpt-3.5-turbo",
+            temperature=0.7,
+            api_key=os.getenv("OPENAI_API_KEY")
+        )
+        
+        # Create service context
+        service_context = ServiceContext.from_defaults(llm=llm)
+        
+        # Load documents (adjust path as needed)
+        if os.path.exists("data"):
+            documents = SimpleDirectoryReader("data").load_data()
+            app.state.index = VectorStoreIndex.from_documents(
+                documents,
+                service_context=service_context
+            )
+        else:
+            # Create empty index if no documents
+            app.state.index = VectorStoreIndex([])
+            
+        app.state.query_engine = app.state.index.as_query_engine()
+        logger.info("LlamaIndex initialization completed successfully")
+    except Exception as e:
+        logger.error(f"Error during startup: {str(e)}")
+        raise
+
+@app.get("/health")
+async def health_check():
+    return {"status": "healthy"}
+
+@app.post("/chat", response_model=ChatResponse)
+async def chat_endpoint(request: ChatRequest):
+    try:
+        # Extract the last user message
+        last_message = next(
+            (msg.content for msg in reversed(request.messages) if msg.role == "user"),
+            None
+        )
+        
+        if not last_message:
+            raise HTTPException(
+                status_code=400,
+                detail="No user message found in the conversation"
+            )
+
+        # Get response from LlamaIndex
+        response = app.state.query_engine.query(
+            last_message,
+            similarity_top_k=3,  # Adjust as needed
+        )
+
+        # Format response
+        return ChatResponse(
+            content=str(response),
+            stop=None,
+            usage={
+                "prompt_tokens": 0,  # Add actual token counting if needed
+                "completion_tokens": 0,
+                "total_tokens": 0
+            }
+        )
+
+    except Exception as e:
+        logger.error(f"Error processing chat request: {str(e)}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=7860)

requirements.txt

@@ -0,0 +1,6 @@
+fastapi==0.68.0
+uvicorn==0.15.0
+llama-index==0.9.3
+python-dotenv==0.19.0
+pydantic==1.8.2
+openai==1.3.0