@leonamnagel9999

Thank you, we need more videos like this to understand the possibilities

@raphauy

Awesome!!! Insta subscribed! Thank you very much for sharing, I will contribute with you.

@kasulejohntrevor5305

Thank you for the video! The document was not uploaded. Was it?

@sir_alist

Круто, 13:00 жду с нетерпением  :)

@RolandoLopezNieto

Great video, thanks

@darwinchan5573

great! keep sharing with us your knowledge and skills

@techwithray8943

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

@leonamnagel9999

Two questions
1 - Why do you prefer Hugging Face Inference for Embeddings? 
2 - Do not need to put the model for embedding?

@tgwashdc

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?

@cvaug6958

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

@crackerbex

How do you add a prompt to the LLM chain so it can answer from documents?

@KunalSharma-f5j

After replicating your structure I am getting 0 in the response of all my prompts
Where am i going wrong? Please explain

@peroforrr7663

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.

@nate5655

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.

@xmi2an

How can i use Chat Prompt Template on ChatOpenAI with memory?

@nntun03

perfect for searching Turing..can i search other words besides Turing?

@DS-ig1bf

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?

@liuchuchenliu2802

Have you successfully debugged with azure openai api? I tried several times, it was fine with openai but not successful with azure

@segarlinktech

good AI

@danzreview

how to combine Prompt and PDF