promtengineer / youttube-tutorial

This repo contains codes covered in the youtube tutorials.

YoutTube-Tutorial

This repo contains codes covered in the youtube tutorials.

To run the Groq RAG example code, use the command streamlit run langchain_groq_rag.py

Video link	Notebook
Getting Started with Groq API
Better RAG: Hybrid Search in LangChain with BM25 and Ensemble
Fine-Tune Your Own Tiny-Llama on Custom Dataset
Run Mixtral 8x7B MoE in Google Colab
GEMINI Pro with LangChain - Chat, MultiModal and Chat with your Documents
Supercharge Your RAG with Contextualized Late Interactions
Advanced RAG with ColBERT in LangChain and LlamaIndex
Claude 3 Introduces Function Calling and Tool Usage
Groq Now Supports Function Calling
Create Financial Agents with Vision 👀 - Powered by Claude 3 Haiku & Opus
MIXTRAL 8x22B MOE: The BEST Open LLM Just got better - RAG and Function Calling
Insanely Fast LLAMA-3 on Groq Playground and API for FREE

youttube-tutorial's Issues

Trouble running code...

Hello, I am having some trouble running the code as is... I have plugged in my GROQ API key and that is loading.

When I run the code using

streamlit run langchain_groq_rag.py

(which took me a while to figure this out, you might want to update your readme :)

I get this error... I have even tried installing Ollama on my Mac... any other tips?

File "/Users/patiman/miniconda3/envs/catholic-chat-app/lib/python3.10/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 535, in _run_script
    exec(code, module.__dict__)
File "/Users/patiman/git/catholic/catholic-chat-app/YoutTube-Tutorial/langchain_groq_rag.py", line 28, in <module>
    st.session_state.vector = FAISS.from_documents(st.session_state.documents, st.session_state.embeddings)
File "/Users/patiman/miniconda3/envs/catholic-chat-app/lib/python3.10/site-packages/langchain_core/vectorstores.py", line 528, in from_documents
    return cls.from_texts(texts, embedding, metadatas=metadatas, **kwargs)
File "/Users/patiman/miniconda3/envs/catholic-chat-app/lib/python3.10/site-packages/langchain_community/vectorstores/faiss.py", line 965, in from_texts
    embeddings = embedding.embed_documents(texts)
File "/Users/patiman/miniconda3/envs/catholic-chat-app/lib/python3.10/site-packages/langchain_community/embeddings/ollama.py", line 204, in embed_documents
    embeddings = self._embed(instruction_pairs)
File "/Users/patiman/miniconda3/envs/catholic-chat-app/lib/python3.10/site-packages/langchain_community/embeddings/ollama.py", line 192, in _embed
    return [self._process_emb_response(prompt) for prompt in iter_]
File "/Users/patiman/miniconda3/envs/catholic-chat-app/lib/python3.10/site-packages/langchain_community/embeddings/ollama.py", line 192, in <listcomp>
    return [self._process_emb_response(prompt) for prompt in iter_]
File "/Users/patiman/miniconda3/envs/catholic-chat-app/lib/python3.10/site-packages/langchain_community/embeddings/ollama.py", line 163, in _process_emb_response
    raise ValueError(f"Error raised by inference endpoint: {e}")