Add template for rag-singlestoredb (#12805)

This change adds a new template for simple RAG using the SingleStoreDB
vectorstore.

Twitter: @alexjpeng

---------

Co-authored-by: Erick Friis <erick@langchain.dev>

templates/rag-singlestoredb/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 LangChain, Inc.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

templates/rag-singlestoredb/README.md

@@ -0,0 +1,69 @@
+
+# rag-singlestoredb
+
+This template performs RAG using SingleStoreDB and OpenAI.
+
+## Environment Setup
+
+This template uses SingleStoreDB as a vectorstore and requires that `SINGLESTOREDB_URL` is set. It should take the form `admin:password@svc-xxx.svc.singlestore.com:port/db_name`
+
+Set the `OPENAI_API_KEY` environment variable to access the OpenAI models.
+
+## Usage
+
+To use this package, you should first have the LangChain CLI installed:
+
+```shell
+pip install -U "langchain-cli[serve]"
+```
+
+To create a new LangChain project and install this as the only package, you can do:
+
+```shell
+langchain app new my-app --package rag-singlestoredb
+```
+
+If you want to add this to an existing project, you can just run:
+
+```shell
+langchain app add rag-singlestoredb
+```
+
+And add the following code to your `server.py` file:
+```python
+from rag_singlestoredb import chain as rag_singlestoredb_chain
+
+add_routes(app, rag_singlestoredb_chain, path="/rag-singlestoredb")
+```
+
+(Optional) Let's now configure LangSmith. 
+LangSmith will help us trace, monitor and debug LangChain applications. 
+LangSmith is currently in private beta, you can sign up [here](https://smith.langchain.com/). 
+If you don't have access, you can skip this section
+
+
+```shell
+export LANGCHAIN_TRACING_V2=true
+export LANGCHAIN_API_KEY=<your-api-key>
+export LANGCHAIN_PROJECT=<your-project>  # if not specified, defaults to "default"
+```
+
+If you are inside this directory, then you can spin up a LangServe instance directly by:
+
+```shell
+langchain serve
+```
+
+This will start the FastAPI app with a server is running locally at 
+[http://localhost:8000](http://localhost:8000)
+
+We can see all templates at [http://127.0.0.1:8000/docs](http://127.0.0.1:8000/docs)
+We can access the playground at [http://127.0.0.1:8000/rag-singlestoredb/playground](http://127.0.0.1:8000/rag-singlestoredb/playground)  
+
+We can access the template from code with:
+
+```python
+from langserve.client import RemoteRunnable
+
+runnable = RemoteRunnable("http://localhost:8000/rag-singlestoredb")
+```

templates/rag-singlestoredb/pyproject.toml

@@ -0,0 +1,28 @@
+[tool.poetry]
+name = "rag-singlestoredb"
+version = "0.0.1"
+description = ""
+authors = [
+    "Alex Peng <apeng@singlestore.com>"
+]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = ">=3.8.1,<4.0"
+langchain = ">=0.0.313, <0.1"
+openai = "^0.28.1"
+singlestoredb = ">=0.8.1"
+tiktoken = "^0.5.1"
+
+[tool.poetry.group.dev.dependencies]
+langchain-cli = ">=0.0.4"
+fastapi = "^0.104.0"
+sse-starlette = "^1.6.5"
+
+[tool.langserve]
+export_module = "rag_singlestoredb"
+export_attr = "chain"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

templates/rag-singlestoredb/rag_singlestoredb.ipynb

@@ -0,0 +1,51 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "681a5d1e",
+   "metadata": {},
+   "source": [
+    "## Connect to template\n",
+    "\n",
+    "In `server.py`, set -\n",
+    "```\n",
+    "add_routes(app, chain_ext, path=\"/rag_singlestore\")\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d774be2a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langserve.client import RemoteRunnable\n",
+    "\n",
+    "rag_app_singlestore = RemoteRunnable(\"http://0.0.0.0:8001/rag_singlestore\")\n",
+    "rag_app_singlestore.invoke(\"How does agent memory work?\")"
+   ]
+  }
+ ],
+ "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/rag-singlestoredb/rag_singlestoredb/__init__.py

@@ -0,0 +1,3 @@
+from rag_singlestoredb.chain import chain
+
+__all__ = ["chain"]

templates/rag-singlestoredb/rag_singlestoredb/chain.py

@@ -0,0 +1,60 @@
+import os
+
+from langchain.chat_models import ChatOpenAI
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.prompts import ChatPromptTemplate
+from langchain.pydantic_v1 import BaseModel
+from langchain.schema.output_parser import StrOutputParser
+from langchain.schema.runnable import RunnableParallel, RunnablePassthrough
+from langchain.vectorstores import SingleStoreDB
+
+if os.environ.get("SINGLESTOREDB_URL", None) is None:
+    raise Exception("Missing `SINGLESTOREDB_URL` environment variable.")
+
+# SINGLESTOREDB_URL takes the form of: "admin:password@host:port/db_name"
+
+## Ingest code - you may need to run this the first time
+# # Load
+# from langchain.document_loaders import WebBaseLoader
+
+# loader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")
+# data = loader.load()
+
+# # Split
+# from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+# text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
+# all_splits = text_splitter.split_documents(data)
+
+# # Add to vectorDB
+# vectorstore = SingleStoreDB.from_documents(
+#     documents=all_splits, embedding=OpenAIEmbeddings()
+# )
+# retriever = vectorstore.as_retriever()
+
+vectorstore = SingleStoreDB(embedding=OpenAIEmbeddings())
+retriever = vectorstore.as_retriever()
+
+# RAG prompt
+template = """Answer the question based only on the following context:
+{context}
+Question: {question}
+"""
+prompt = ChatPromptTemplate.from_template(template)
+
+# RAG
+model = ChatOpenAI()
+chain = (
+    RunnableParallel({"context": retriever, "question": RunnablePassthrough()})
+    | prompt
+    | model
+    | StrOutputParser()
+)
+
+
+# Add typing for input
+class Question(BaseModel):
+    __root__: str
+
+
+chain = chain.with_types(input_type=Question)