davila7 / file-gpt

Start a chat with any document with Ada Embedding and Davinci Completion

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

FileGPT 🤖

Read the article to know how it works: Medium Article

With File GPT you will be able to extract all the information from a file. You will obtain the transcription, the embedding of each segment and also ask questions to the file through a chat.

All code was written with the help of Code GPT

Captura de Pantalla 2023-02-08 a la(s) 9 16 43 p  m



Features

  • Read any pdf, docx, txt or csv file
  • Embedding texts segments with Langchain and OpenAI (text-embedding-ada-002)
  • Chat with the file using streamlit-chat and LangChain QA with source and (text-davinci-003)

Running Locally

  1. Clone the repository
git clone https://github.com/davila7/file-gpt
cd file-gpt
  1. Install dependencies

These dependencies are required to install with the requirements.txt file:

  • openai
  • pypdf
  • scikit-learn
  • numpy
  • tiktoken
  • docx2txt
  • langchain
  • pydantic
  • typing
  • faiss-cpu
  • streamlit_chat
pip install -r requirements.txt
  1. Run the Streamlit server
streamlit run app.py

About

Start a chat with any document with Ada Embedding and Davinci Completion

License:MIT License


Languages

Language:Python 100.0%