├── .streamlit └── config.toml ├── requirements.txt ├── YouTube-Assistant.png ├── Dockerfile ├── README.md ├── main.py ├── langchain_helper.py └── .gitignore /.streamlit/config.toml: -------------------------------------------------------------------------------- 1 | [theme] 2 | base="dark" 3 | primaryColor="purple" -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | python-dotenv 2 | langchain 3 | openai 4 | youtube-transcript-api 5 | faiss-cpu 6 | streamlit -------------------------------------------------------------------------------- /YouTube-Assistant.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rishabkumar7/youtube-assistant-langchain/HEAD/YouTube-Assistant.png -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- 1 | FROM python:3.9.2 2 | WORKDIR youtube-assistant 3 | COPY requirements.txt requirements.txt 4 | RUN pip3 install -r requirements.txt 5 | COPY . . 6 | EXPOSE 8501 7 | CMD ["streamlit", "run", "main.py", "--server.port=8501", "--server.address=0.0.0.0"] -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # YouTube Assistant 2 | 3 | Ask questions about any YouTube video to this LLM powered assistant. 4 | 5 | ## Running it locally 6 | 7 | Install the required packages: 8 | 9 | ```bash 10 | pip install -r requirements.txt 11 | ``` 12 | 13 | Run the streamlit app: 14 | 15 | ```bash 16 | streamlit run main.py 17 | ``` 18 | 19 | ![YouTube Assistant App](/YouTube-Assistant.png) 20 | 21 | ## Hosted On 22 | 23 | The web-app uses streamlit and is hosted on [Azure Container Apps.](https://azure.microsoft.com/en-ca/products/container-apps) 24 | 25 | ## Author 26 | 27 | - Twitter: [@rishabkumar7](https://twitter.com/rishabk7) 28 | - LinkedIn: [rishabkumar7](https://linkedin.com/in/rishabkumar7) -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- 1 | import streamlit as st 2 | import langchain_helper as lch 3 | import textwrap 4 | 5 | st.title("YouTube Assistant") 6 | 7 | with st.sidebar: 8 | with st.form(key='my_form'): 9 | youtube_url = st.sidebar.text_area( 10 | label="What is the YouTube video URL?", 11 | max_chars=50 12 | ) 13 | query = st.sidebar.text_area( 14 | label="Ask me about the video?", 15 | max_chars=50, 16 | key="query" 17 | ) 18 | openai_api_key = st.sidebar.text_input( 19 | label="OpenAI API Key", 20 | key="langchain_search_api_key_openai", 21 | max_chars=50, 22 | type="password" 23 | ) 24 | "[Get an OpenAI API key](https://platform.openai.com/account/api-keys)" 25 | "[View the source code](https://github.com/rishabkumar7/pets-name-langchain/tree/main)" 26 | submit_button = st.form_submit_button(label='Submit') 27 | 28 | if query and youtube_url: 29 | if not openai_api_key: 30 | st.info("Please add your OpenAI API key to continue.") 31 | st.stop() 32 | else: 33 | db = lch.create_db_from_youtube_video_url(youtube_url) 34 | response, docs = lch.get_response_from_query(db, query) 35 | st.subheader("Answer:") 36 | st.text(textwrap.fill(response, width=85)) -------------------------------------------------------------------------------- /langchain_helper.py: -------------------------------------------------------------------------------- 1 | from langchain.document_loaders import YoutubeLoader 2 | from langchain.text_splitter import RecursiveCharacterTextSplitter 3 | from langchain.embeddings.openai import OpenAIEmbeddings 4 | from langchain.vectorstores import FAISS 5 | from langchain.llms import OpenAI 6 | from langchain import PromptTemplate 7 | from langchain.chains import LLMChain 8 | from dotenv import load_dotenv 9 | 10 | 11 | load_dotenv() 12 | embeddings = OpenAIEmbeddings() 13 | 14 | 15 | def create_db_from_youtube_video_url(video_url: str) -> FAISS: 16 | loader = YoutubeLoader.from_youtube_url(video_url) 17 | transcript = loader.load() 18 | 19 | text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100) 20 | docs = text_splitter.split_documents(transcript) 21 | 22 | db = FAISS.from_documents(docs, embeddings) 23 | return db 24 | 25 | 26 | def get_response_from_query(db, query, k=4): 27 | """ 28 | text-davinci-003 can handle up to 4097 tokens. Setting the chunksize to 1000 and k to 4 maximizes 29 | the number of tokens to analyze. 30 | """ 31 | 32 | docs = db.similarity_search(query, k=k) 33 | docs_page_content = " ".join([d.page_content for d in docs]) 34 | 35 | llm = OpenAI(model_name="text-davinci-003") 36 | 37 | prompt = PromptTemplate( 38 | input_variables=["question", "docs"], 39 | template=""" 40 | You are a helpful assistant that that can answer questions about youtube videos 41 | based on the video's transcript. 42 | 43 | Answer the following question: {question} 44 | By searching the following video transcript: {docs} 45 | 46 | Only use the factual information from the transcript to answer the question. 47 | 48 | If you feel like you don't have enough information to answer the question, say "I don't know". 49 | 50 | Your answers should be verbose and detailed. 51 | """, 52 | ) 53 | 54 | chain = LLMChain(llm=llm, prompt=prompt) 55 | 56 | response = chain.run(question=query, docs=docs_page_content) 57 | response = response.replace("\n", "") 58 | return response, docs -------------------------------------------------------------------------------- /.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 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 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 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # pdm 105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 106 | #pdm.lock 107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 108 | # in version control. 109 | # https://pdm.fming.dev/#use-with-ide 110 | .pdm.toml 111 | 112 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 113 | __pypackages__/ 114 | 115 | # Celery stuff 116 | celerybeat-schedule 117 | celerybeat.pid 118 | 119 | # SageMath parsed files 120 | *.sage.py 121 | 122 | # Environments 123 | .env 124 | .venv 125 | env/ 126 | venv/ 127 | ENV/ 128 | env.bak/ 129 | venv.bak/ 130 | 131 | # Spyder project settings 132 | .spyderproject 133 | .spyproject 134 | 135 | # Rope project settings 136 | .ropeproject 137 | 138 | # mkdocs documentation 139 | /site 140 | 141 | # mypy 142 | .mypy_cache/ 143 | .dmypy.json 144 | dmypy.json 145 | 146 | # Pyre type checker 147 | .pyre/ 148 | 149 | # pytype static type analyzer 150 | .pytype/ 151 | 152 | # Cython debug symbols 153 | cython_debug/ 154 | 155 | # PyCharm 156 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 157 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 158 | # and can be added to the global gitignore or merged into this file. For a more nuclear 159 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 160 | #.idea/ 161 | --------------------------------------------------------------------------------