search

mayooear / gpt4-pdf-chatbot-langchain

GPT4 & LangChain Chatbot for large PDF docs
https://www.youtube.com/watch?v=ih9PBGVVOO4
14.73k stars 3k forks source link

Does the new GPTs release from openAI remove the need for this kind of work? #431

Closed irwinwilliams closed 4 months ago

irwinwilliams commented 7 months ago

GPTs looks like they will let you talk to PDFs by uploading them and providing a useful prompt. Doesn't that remove the need for an approach like this?

dosubot[bot] commented 7 months ago

🤖

Hello @irwinwilliams,

Nice to meet you! I'm Dosu, a bot here to assist you with issues, answer your questions, and help you contribute to this repository. While we're waiting for a human maintainer to join, I'm here to provide support and help you get the information you need.

I appreciate your patience, and I'm currently looking into your query about the new GPTs release from OpenAI and its implications on our project. I'll provide a full answer shortly.

dosubot[bot] commented 7 months ago

🤖

The new GPTs release from OpenAI indeed introduces the ability to interact with PDFs by uploading them and providing a prompt. However, the gpt4-pdf-chatbot-langchain repository offers a more specialized and customizable approach for handling large PDF files, which may still be beneficial depending on the specific use case.

The gpt4-pdf-chatbot-langchain repository is designed to work specifically with large PDF files, converting them into embeddings for later retrieval of similar documents. It integrates with LangChain, a framework that facilitates the creation of scalable AI/LLM apps and chatbots, and Pinecone, a vectorstore used for storing embeddings and the text of your PDF files. This repository also allows for customization of the chatbot prompt and the model name used in the OpenAI API call, and includes an API endpoint that handles chat requests (source).

On the other hand, the new GPTs release from OpenAI can load PDF files, split the text into chunks, create embeddings for these chunks, and store the embeddings in a vector store (source). However, it does not appear to have the same level of customization and integration with other tools as the gpt4-pdf-chatbot-langchain repository.

Therefore, while the new GPTs release from OpenAI may simplify the process of interacting with PDFs, the gpt4-pdf-chatbot-langchain repository may still be useful for more complex or specialized use cases.

Sources

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.

dosubot[bot] commented 4 months ago

Hi, @irwinwilliams

I'm helping the gpt4-pdf-chatbot-langchain team manage their backlog and am marking this issue as stale. From what I understand, you raised a question about the relevance of your work in light of the release of GPTs from OpenAI, and Dosu-bot responded, highlighting the specialized and customizable approach offered by the gpt4-pdf-chatbot-langchain repository for handling large PDF files. They emphasized its integration with LangChain and Pinecone for scalable AI/LLM apps and chatbots, and suggested that it may still be useful for more complex or specialized use cases despite the release of GPTs from OpenAI.

Could you please confirm if this issue is still relevant to the latest version of the gpt4-pdf-chatbot-langchain repository? If it is, please let the gpt4-pdf-chatbot-langchain team know by commenting on the issue. Otherwise, feel free to close the issue yourself, or it will be automatically closed in 7 days. Thank you!