Spaces:
Sleeping
Sleeping
File size: 2,127 Bytes
e878e8a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 |
"""
This works.
reference: https://www.youtube.com/watch?v=CPgp8MhmGVY
"""
# Imports
import gradio as gr
from langchain_community.llms import Ollama
from langchain_community.document_loaders import WebBaseLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
# dont use this embeddings
# from langchain.embeddings import GPT4AllEmbeddings
# from langchain_community.embeddings import GPT4AllEmbeddings
# from langchain.embeddings import SentenceTransformerEmbeddings
from langchain_community.embeddings import SentenceTransformerEmbeddings
# from langchain.vectorstores import Chroma
from langchain_community.vectorstores import Chroma
from langchain.chains import RetrievalQA
# Instantiate the Ollama model
ollama = Ollama(
# base_url="http://localhost:3000",
model="llama3"
)
# Load the webpage content using WebBaseLoader
loader = WebBaseLoader("https://en.wikipedia.org/wiki/Tsai_Ing-wen")
data = loader.load()
# Split the text into manageable chunks using RecursiveCharacterTextSplitter
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
all_splits = text_splitter.split_documents(data)
# Instantiate SentenceTransformers embeddings with the specified model
sentence_embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
# Create the vector store from the document splits and embeddings
vectorstore = Chroma.from_documents(documents=all_splits, embedding=sentence_embeddings)
# Create a QA chain using the Ollama model and the vector store retriever
qachain = RetrievalQA.from_chain_type(ollama, retriever=vectorstore.as_retriever())
# Function to handle the question and return the answer
def answer_question(question):
response = qachain({"query": question})
return response["result"]
# Create a Gradio interface
interface = gr.Interface(
fn=answer_question,
inputs="text",
outputs="text",
title="RAG Model QA Interface",
description="Ask a question about Tsai Ing-wen and get an answer from the Retrieval-Augmented Generation model.",
)
# Launch the Gradio interface
interface.launch(share=True)
|