Update multi query template README, ntbk (#12356)

templates/rag-pinecone-multi-query/README.md

@@ -14,3 +14,38 @@ This template uses Pinecone as a vectorstore and requires that `PINECONE_API_KEY
 
 Be sure that `OPENAI_API_KEY` is set in order to the OpenAI models.
 
+## App
+
+Example `server.py`:
+```
+from fastapi import FastAPI
+from langserve import add_routes
+from rag_pinecone_multi_query.chain import chain
+
+app = FastAPI()
+
+# Edit this to add the chain you want to add
+add_routes(app, chain, path="rag_pinecone_multi_query")
+
+if __name__ == "__main__":
+    import uvicorn
+
+    uvicorn.run(app, host="0.0.0.0", port=8001)
+```
+
+Run:
+```
+python app/server.py
+```
+
+Check endpoint:
+```
+http://0.0.0.0:8001/docs
+```
+
+See `rag_pinecone_multi_query.ipynb` for example usage - 
+```
+from langserve.client import RemoteRunnable
+rag_app_pinecone = RemoteRunnable('http://0.0.0.0:8001/rag_pinecone_multi_query')
+rag_app_pinecone.invoke("What are the different types of agent memory")
+```

templates/rag-pinecone-multi-query/rag_pinecone_multi_query.ipynb

@@ -11,13 +11,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "id": "d774be2a",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'The different types of agent memory mentioned in the context are short-term memory, long-term memory, explicit/declarative memory, and implicit/procedural memory.'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "from langserve.client import RemoteRunnable\n",
-    "rag_app_pinecone = RemoteRunnable('http://localhost:8000/rag-pinecone-multi-query')\n",
+    "rag_app_pinecone = RemoteRunnable('http://0.0.0.0:8001/rag_pinecone_multi_query')\n",
     "rag_app_pinecone.invoke(\"What are the different types of agent memory\")"
    ]
   }