Upload 3 files

README_JB.md

@@ -0,0 +1,15 @@
+# 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](https://youtu.be/S53BanCP14c) |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](http://tinyurl.com/2nxdv2m8)|
+| [Better RAG: Hybrid Search in LangChain with BM25 and Ensemble](https://youtu.be/r2m9DbEmeqI) |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](http://tinyurl.com/33wc8sav)|
+| [Fine-Tune Your Own Tiny-Llama on Custom Dataset](https://youtu.be/OVqe6GTrDFM) |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](http://tinyurl.com/4eny9cvc)|
+| [Run Mixtral 8x7B MoE in Google Colab](https://youtu.be/Zo3CTapKJ4I) |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](http://tinyurl.com/2nn5snb4)|
+| [GEMINI Pro with LangChain - Chat, MultiModal and Chat with your Documents](https://youtu.be/7h8ZHSkAkas) |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://tinyurl.com/28bw3ntv)|
+| [GEMINI Pro with LangChain - Chat, MultiModal and Chat with your Documents](https://youtu.be/7h8ZHSkAkas) |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://tinyurl.com/28bw3ntv)|
+
+

langchain_groq_rag_JB.py

@@ -0,0 +1,99 @@
+# JB:
+# LangChainDeprecationWarning: Importing embeddings from langchain is deprecated. 
+# Importing from langchain will no longer be supported as of langchain==0.2.0.
+# Please import from langchain-community instead:
+# `from langchain_community.embeddings import FastEmbedEmbeddings`.
+# To install langchain-community run `pip install -U langchain-community`.
+from langchain_community.embeddings import FastEmbedEmbeddings
+
+import os
+import streamlit as st
+from langchain_groq import ChatGroq
+from langchain_community.document_loaders import WebBaseLoader
+from langchain_community.embeddings import OllamaEmbeddings
+
+# JB:
+from langchain.embeddings import FastEmbedEmbeddings
+
+# from langchain_community.vectorstores import FAISS
+# from langchain.vectorstores import Chroma
+from langchain_community.vectorstores import Chroma
+
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain_core.prompts import ChatPromptTemplate
+from langchain.chains import create_retrieval_chain
+import time
+from dotenv import load_dotenv
+
+load_dotenv()  #
+
+# groq_api_key = os.environ['GROQ_API_KEY']
+groq_api_key = "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" # os.environ['GROQ_API_KEY']
+print("groq_api_key: ", groq_api_key)
+
+
+if "vector" not in st.session_state:
+
+    # st.session_state.embeddings = OllamaEmbeddings() # ORIGINAL
+    st.session_state.embeddings = FastEmbedEmbeddings() # JB
+
+
+    st.session_state.loader = WebBaseLoader("https://paulgraham.com/greatwork.html")
+    st.session_state.docs = st.session_state.loader.load()
+
+    st.session_state.text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    st.session_state.documents = st.session_state.text_splitter.split_documents( st.session_state.docs)
+    # st.session_state.vector = FAISS.from_documents(st.session_state.documents, st.session_state.embeddings) # ORIGINAL
+    # ZIE: 
+    # ZIE VOOR EEN APP MET CHROMADB:
+    # https://github.com/vndee/local-rag-example/blob/main/rag.py
+    # https://raw.githubusercontent.com/vndee/local-rag-example/main/rag.py
+    # Chroma.from_documents(documents=chunks, embedding=FastEmbedEmbeddings())
+    st.session_state.vector = Chroma.from_documents(st.session_state.documents, st.session_state.embeddings) # JB
+
+
+# st.title("Chat with Docs - Groq Edition :) ")
+st.title("Literature Based Research (LBR) - Alexander Unzicker and Jan Bours - Chat with Docs - Groq Edition (Very Fast!) ")
+
+
+llm = ChatGroq(
+            groq_api_key=groq_api_key, 
+            model_name='mixtral-8x7b-32768'
+    )
+
+prompt = ChatPromptTemplate.from_template("""
+Answer the following question based only on the provided context. 
+Think step by step before providing a detailed answer. 
+I will tip you $200 if the user finds the answer helpful. 
+<context>
+{context}
+</context>
+
+Question: {input}""")
+
+document_chain = create_stuff_documents_chain(llm, prompt)
+
+retriever = st.session_state.vector.as_retriever()
+retrieval_chain = create_retrieval_chain(retriever, document_chain)
+
+prompt = st.text_input("Input your prompt here")
+
+
+# If the user hits enter
+if prompt:
+    # Then pass the prompt to the LLM
+    start = time.process_time()
+    response = retrieval_chain.invoke({"input": prompt})
+    print(f"Response time: {time.process_time() - start}")
+
+    st.write(response["answer"])
+
+    # With a streamlit expander
+    with st.expander("Document Similarity Search"):
+        # Find the relevant chunks
+        for i, doc in enumerate(response["context"]):
+            # print(doc)
+            # st.write(f"Source Document # {i+1} : {doc.metadata['source'].split('/')[-1]}")
+            st.write(doc.page_content)
+            st.write("--------------------------------")

requirements.txt

@@ -0,0 +1,13 @@
+streamlit
+groq
+langchain
+langchain-groq
+python-dotenv
+beautifulsoup4
+faiss-cpu
+
+# JB:
+chromadb
+fastembed
+
+ollama