PDF Data Extraction Chatbot

Harness Python, Langchain, Gemini (Google's AI), and ChromaDB (vector database) to seamlessly extract data from PDF documents, enriching your chatbot's conversational abilities with invaluable insights

Tags

• #AI
• #NLP
• #Python
• #Chatbot
• #Langchain
• #PDFDataExtraction
• #GeminiAI (Google)

Steps to use

• uploda file with pdf extention
• click in 'Submit & process' button
• now, you can use the chatbot to explore the file

Ask examples:

resume the file

list the main characters

Execute

create ".env" file

GOOGLE_API_KEY= <<< SET YOUT GOOGLE_API_KEY HERE >>>

Commands

conda activate project-env

conda env update -n project-env -f ./env.yml

streamlit run src/main.py
 

Links

github

docs.lanchain