Skip to content

Chandrakant817/Chat-with-PDF-using-LangChain

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Chat-with-PDF-using-LangChain

Chat with your PDF data using using LangChain Framework.

System Setup:

Step 1. Create a virtual environment

conda create -p myenv python=3.9 -y

step 2. Activate the environment:

conda activate myenv/

step 3. Install all the requirements:

pip install -r requirements.txt

step 4. start writing the code, with standard file name as main.py

Flow

image

High Level Architecture

image

Steps:

  1. Upload the PDF Files
  2. Extract the content from the PDF
  3. Split content into Chunk
  4. Do Embeddings of the data (Download embeddings from the OpenAI)
  5. Store Data into Vector Store (eg: FAISS and Croma)
  6. User can pass a Prompt
  7. Based on User query, Similarity search will apply
  8. Get the Output.

Output

image

References

  1. https://youtu.be/5Ghv-F1wF_0?si=7Y2yEV6k6y89VOeo

Releases

No releases published

Packages

No packages published