Update SQL templates (#12464)

templates/sql-ollama/README.md

@@ -15,11 +15,4 @@ Also follow instructions to download your LLM of interest:
 
 This template includes an example DB of 2023 NBA rosters.
 
-You can see instructions to build this DB [here](https://github.com/facebookresearch/llama-recipes/blob/main/demo_apps/StructuredLlama.ipynb).
-
-## Installation
-
-```bash
-# from inside your LangServe instance
-poe add sql-ollama
-```
+You can see instructions to build this DB [here](https://github.com/facebookresearch/llama-recipes/blob/main/demo_apps/StructuredLlama.ipynb).

templates/sql-ollama/sql-ollama.ipynb

@@ -0,0 +1,54 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "d55f5fd9-21eb-433d-9259-0a588d9197c0",
+   "metadata": {},
+   "source": [
+    "## Run Template\n",
+    "\n",
+    "In `server.py`, set -\n",
+    "```\n",
+    "add_routes(app, chain, path=\"/sql_ollama\")\n",
+    "```\n",
+    "\n",
+    "This template includes an example DB of 2023 NBA rosters.\n",
+    "\n",
+    "We can  ask questions related to NBA players. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "50c27e82-92d8-4fa1-8bc4-b6544e59773d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langserve.client import RemoteRunnable\n",
+    "sql_app = RemoteRunnable('http://0.0.0.0:8001/sql_ollama')\n",
+    "sql_app.invoke({\"question\": \"What team is Klay Thompson on?\"})"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

templates/sql-ollama/sql_ollama/chain.py

@@ -3,6 +3,7 @@ from pathlib import Path
 from langchain.chat_models import ChatOllama
 from langchain.memory import ConversationBufferMemory
 from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
+from langchain.pydantic_v1 import BaseModel
 from langchain.schema.output_parser import StrOutputParser
 from langchain.schema.runnable import RunnableLambda, RunnablePassthrough
 from langchain.utilities import SQLDatabase
@@ -82,8 +83,12 @@ prompt_response = ChatPromptTemplate.from_messages(
     ]
 )
 
+# Supply the input types to the prompt 
+class InputType(BaseModel):
+    question: str
+
 chain = (
-    RunnablePassthrough.assign(query=sql_response_memory)
+    RunnablePassthrough.assign(query=sql_response_memory).with_types(input_type=InputType)
     | RunnablePassthrough.assign(
         schema=get_schema,
         response=lambda x: db.run(x["query"]),