├── .gitignore ├── LICENSE ├── README.md ├── app.py ├── ingest_data.py ├── query_data.py └── requirements.txt /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | pip-wheel-metadata/ 24 | share/python-wheels/ 25 | *.egg-info/ 26 | .installed.cfg 27 | *.egg 28 | MANIFEST 29 | 30 | # PyInstaller 31 | # Usually these files are written by a python script from a template 32 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 33 | *.manifest 34 | *.spec 35 | 36 | # Installer logs 37 | pip-log.txt 38 | pip-delete-this-directory.txt 39 | 40 | # Unit test / coverage reports 41 | htmlcov/ 42 | .tox/ 43 | .nox/ 44 | .coverage 45 | .coverage.* 46 | .cache 47 | nosetests.xml 48 | coverage.xml 49 | *.cover 50 | *.py,cover 51 | .hypothesis/ 52 | .pytest_cache/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | target/ 76 | 77 | # Jupyter Notebook 78 | .ipynb_checkpoints 79 | 80 | # IPython 81 | profile_default/ 82 | ipython_config.py 83 | 84 | # pyenv 85 | .python-version 86 | 87 | # pipenv 88 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 89 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 90 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 91 | # install all needed dependencies. 92 | #Pipfile.lock 93 | 94 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow 95 | __pypackages__/ 96 | 97 | # Celery stuff 98 | celerybeat-schedule 99 | celerybeat.pid 100 | 101 | # SageMath parsed files 102 | *.sage.py 103 | 104 | # Environments 105 | .env 106 | .venv 107 | env/ 108 | venv/ 109 | ENV/ 110 | env.bak/ 111 | venv.bak/ 112 | 113 | # Spyder project settings 114 | .spyderproject 115 | .spyproject 116 | 117 | # Rope project settings 118 | .ropeproject 119 | 120 | # mkdocs documentation 121 | /site 122 | 123 | # mypy 124 | .mypy_cache/ 125 | .dmypy.json 126 | dmypy.json 127 | 128 | # Pyre type checker 129 | .pyre/ 130 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2023 Harrison Chase 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Chat-LangChain-ReadTheDocs 2 | 3 | Create a ChatGPT like experience over your ReadTheDocs using [LangChain](https://github.com/hwchase17/langchain). 4 | 5 | 6 | ## 📊 Example Data 7 | This repo uses the [LangChain Documentation](https://langchain.readthedocs.io/en/latest/) as an example. 8 | 9 | ## 🧑 Instructions for ingesting your own ReadTheDocs documentation 10 | 11 | Run the following command to download html for a given website. Replace `https://langchain.readthedocs.io/en/latest/` with a URL to your website. 12 | 13 | ```shell 14 | wget -r -A.html https://langchain.readthedocs.io/en/latest/ 15 | ``` 16 | 17 | ## Ingest data 18 | 19 | The only thing that is needed is to be done to ingest data is run `python ingest_data.py` 20 | 21 | ## Query data 22 | Custom prompts are used to ground the answers in LangChain Documentation files. 23 | 24 | ## Running the Application 25 | 26 | By running `python app.py` from the command line you can easily interact with your ChatGPT over your own data. 27 | -------------------------------------------------------------------------------- /app.py: -------------------------------------------------------------------------------- 1 | import pickle 2 | from query_data import get_chain 3 | 4 | 5 | if __name__ == "__main__": 6 | with open("vectorstore.pkl", "rb") as f: 7 | vectorstore = pickle.load(f) 8 | qa_chain = get_chain(vectorstore) 9 | chat_history = [] 10 | print("Chat with your docs!") 11 | while True: 12 | print("Human:") 13 | question = input() 14 | result = qa_chain({"question": question, "chat_history": chat_history}) 15 | chat_history.append((question, result["answer"])) 16 | print("AI:") 17 | print(result["answer"]) 18 | -------------------------------------------------------------------------------- /ingest_data.py: -------------------------------------------------------------------------------- 1 | from langchain.text_splitter import RecursiveCharacterTextSplitter 2 | from langchain.document_loaders import ReadTheDocsLoader 3 | from langchain.vectorstores.faiss import FAISS 4 | from langchain.embeddings import OpenAIEmbeddings 5 | import pickle 6 | 7 | # Load Data 8 | loader = ReadTheDocsLoader("langchain.readthedocs.io") 9 | raw_documents = loader.load() 10 | 11 | # Split text 12 | text_splitter = RecursiveCharacterTextSplitter() 13 | documents = text_splitter.split_documents(raw_documents) 14 | 15 | 16 | # Load Data to vectorstore 17 | embeddings = OpenAIEmbeddings() 18 | vectorstore = FAISS.from_documents(documents, embeddings) 19 | 20 | 21 | # Save vectorstore 22 | with open("vectorstore.pkl", "wb") as f: 23 | pickle.dump(vectorstore, f) 24 | -------------------------------------------------------------------------------- /query_data.py: -------------------------------------------------------------------------------- 1 | from langchain.prompts.prompt import PromptTemplate 2 | from langchain.llms import OpenAI 3 | from langchain.chains import ChatVectorDBChain 4 | 5 | _template = """Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question. 6 | You can assume the question about LangChain. 7 | 8 | Chat History: 9 | {chat_history} 10 | Follow Up Input: {question} 11 | Standalone question:""" 12 | CONDENSE_QUESTION_PROMPT = PromptTemplate.from_template(_template) 13 | 14 | template = """You are an AI assistant for the open source library LangChain. The documentation is located at https://langchain.readthedocs.io. 15 | You are given the following extracted parts of a long document and a question. Provide a conversational answer with a hyperlink to the documentation. 16 | You should only use hyperlinks that are explicitly listed as a source in the context. Do NOT make up a hyperlink that is not listed. 17 | If the question includes a request for code, provide a code block directly from the documentation. 18 | If you don't know the answer, just say "Hmm, I'm not sure." Don't try to make up an answer. 19 | If the question is not about LangChain, politely inform them that you are tuned to only answer questions about LangChain. 20 | 21 | Question: {question} 22 | ========= 23 | {context} 24 | ========= 25 | Answer in Markdown:""" 26 | QA_PROMPT = PromptTemplate(template=template, input_variables=["question", "context"]) 27 | 28 | 29 | def get_chain(vectorstore): 30 | llm = OpenAI(temperature=0) 31 | qa_chain = ChatVectorDBChain.from_llm( 32 | llm, 33 | vectorstore, 34 | qa_prompt=QA_PROMPT, 35 | condense_question_prompt=CONDENSE_QUESTION_PROMPT, 36 | ) 37 | return qa_chain 38 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | langchain 2 | openai 3 | unstructured 4 | faiss-cpu 5 | bs4 6 | --------------------------------------------------------------------------------