Add template for gpt-crawler (#13625)

Template for RAG using
[gpt-crawler](https://github.com/BuilderIO/gpt-crawler).

---------

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

templates/rag-gpt-crawler/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-gpt-crawler/README.md

@@ -0,0 +1,92 @@
+
+# rag-gpt-crawler
+
+GPT-crawler will crawl websites to produce files for use in custom GPTs or other apps (RAG).
+
+This template uses [gpt-crawler](https://github.com/BuilderIO/gpt-crawler) to build a RAG app
+
+## Environment Setup
+
+Set the `OPENAI_API_KEY` environment variable to access the OpenAI models.
+
+## Crawling
+
+Run GPT-crawler to extact content from a set of urls, using the config file in GPT-crawler repo.
+
+Here is example config for LangChain use-case docs:
+
+```
+export const config: Config = {
+  url: "https://python.langchain.com/docs/use_cases/",
+  match: "https://python.langchain.com/docs/use_cases/**",
+  selector: ".docMainContainer_gTbr",
+  maxPagesToCrawl: 10,
+  outputFileName: "output.json",
+};
+```
+
+Then, run this as described in the [gpt-crawler](https://github.com/BuilderIO/gpt-crawler) README:
+
+```
+npm start
+```
+
+And copy the `output.json` file into the folder containing this README.
+
+## Usage
+
+To use this package, you should first have the LangChain CLI installed:
+
+```shell
+pip install -U langchain-cli
+```
+
+To create a new LangChain project and install this as the only package, you can do:
+
+```shell
+langchain app new my-app --package rag-gpt-crawler
+```
+
+If you want to add this to an existing project, you can just run:
+
+```shell
+langchain app add rag-gpt-crawler
+```
+
+And add the following code to your `server.py` file:
+```python
+from rag_chroma import chain as rag_gpt_crawler
+
+add_routes(app, rag_gpt_crawler, path="/rag-gpt-crawler")
+```
+
+(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-gpt-crawler/playground](http://127.0.0.1:8000/rag-gpt-crawler/playground)  
+
+We can access the template from code with:
+
+```python
+from langserve.client import RemoteRunnable
+
+runnable = RemoteRunnable("http://localhost:8000/rag-gpt-crawler")
+```

templates/rag-gpt-crawler/pyproject.toml

@@ -0,0 +1,28 @@
+[tool.poetry]
+name = "rag-gpt-crawler"
+version = "0.1.0"
+description = ""
+authors = [
+    "Lance Martin <lance@langchain.dev>",
+]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = ">=3.8.1,<4.0"
+langchain = ">=0.0.325"
+openai = "<2"
+tiktoken = ">=0.5.1"
+chromadb = ">=0.4.14"
+
+[tool.poetry.group.dev.dependencies]
+langchain-cli = ">=0.0.15"
+
+[tool.langserve]
+export_module = "rag_gpt_crawler"
+export_attr = "chain"
+
+[build-system]
+requires = [
+    "poetry-core",
+]
+build-backend = "poetry.core.masonry.api"

templates/rag-gpt-crawler/rag_gpt_crawler.ipynb

@@ -0,0 +1,51 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "681a5d1e",
+   "metadata": {},
+   "source": [
+    "## Run Template\n",
+    "\n",
+    "In `server.py`, set -\n",
+    "```\n",
+    "add_routes(app, chain_rag_conv, path=\"/rag-gpt-crawler\")\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d774be2a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langserve.client import RemoteRunnable\n",
+    "\n",
+    "rag_app = RemoteRunnable(\"http://localhost:8001/rag-gpt-crawler\")\n",
+    "rag_app.invoke(\"How does summarization 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-gpt-crawler/rag_gpt_crawler/__init__.py

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

templates/rag-gpt-crawler/rag_gpt_crawler/chain.py

@@ -0,0 +1,62 @@
+import json
+from pathlib import Path
+
+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 import Document
+from langchain.schema.output_parser import StrOutputParser
+from langchain.schema.runnable import RunnableParallel, RunnablePassthrough
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import Chroma
+
+# Load output from gpt crawler
+path_to_gptcrawler = Path(__file__).parent.parent / "output.json"
+data = json.loads(Path(path_to_gptcrawler).read_text())
+docs = [
+    Document(
+        page_content=dict_["html"],
+        metadata={"title": dict_["title"], "url": dict_["url"]},
+    )
+    for dict_ in data
+]
+
+# Split
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+all_splits = text_splitter.split_documents(docs)
+
+# Add to vectorDB
+vectorstore = Chroma.from_documents(
+    documents=all_splits,
+    collection_name="rag-gpt-builder",
+    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)
+
+# LLM
+model = ChatOpenAI()
+
+# RAG chain
+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)