Awesome!!! Insta subscribed! Thank you very much for sharing, I will contribute with you.
Thank you for the video! The document was not uploaded. Was it?
Круто, 13:00 жду с нетерпением :)
Great video, thanks
great! keep sharing with us your knowledge and skills
Timestamp 1. Build a basic Chatbot: https://youtu.be/ROoGbFrvuwM?t=76 2. Build a Chatbot to Chat with PDF: https://youtu.be/ROoGbFrvuwM?t=295
Two questions 1 - Why do you prefer Hugging Face Inference for Embeddings? 2 - Do not need to put the model for embedding?
Best yet! Thank you! If the pdf has a structured table, will the split and encode destroy easy extraction of meaningful relationships in a query?
Hi, I don't know if thing had change but the interface its different now. Now you need to upsert the pdf file before being able to chat. So I tried using the default model from hugging face but got a problem about dimension, model was 768 but Pinecone needed 1024. I found a model for 1024 (intfloat/multilingual-e5-large) but got a "fetch failed" error. I looked for the same PDF you using on your video and still got the same error. But then I got a smaller one and it worked. So you know if it could be becaue I'm using free version of pinecone and doesn't allow me big files? or that i'm hosting flowise in hugginface? thanks for the video by the way
How do you add a prompt to the LLM chain so it can answer from documents?
After replicating your structure I am getting 0 in the response of all my prompts Where am i going wrong? Please explain
Hello, 🎉 great content! I would like to request a video on a solution for chatting on PDFs using an open-source model from Hugging Face that utilizes GPU and ensures data privacy.
Do you think i can setup flowise to read a folder locally for csvs looking for a name and then using those csvs or pdfs i guess, to talk about data. Instead of the built in download for csv agent.
How can i use Chat Prompt Template on ChatOpenAI with memory?
perfect for searching Turing..can i search other words besides Turing?
Great content. question! I tried it and it seems answers are restricted to the content of the doc and can’t go out of context. Is there any way around that so it can respond like the normal ChatGPT and also refer to the doc?
Have you successfully debugged with azure openai api? I tried several times, it was fine with openai but not successful with azure
good AI
how to combine Prompt and PDF
@leonamnagel9999