| import os |
| import gradio as gr |
| from langchain_community.document_loaders import PyPDFLoader |
| from langchain_text_splitters import RecursiveCharacterTextSplitter |
| from langchain_huggingface import HuggingFaceEmbeddings |
| from langchain_chroma import Chroma |
| from langchain_groq import ChatGroq |
| from langchain_core.prompts import ChatPromptTemplate |
| from langchain_core.output_parsers import StrOutputParser |
|
|
| embeddings=HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2") |
| llm=ChatGroq(model="llama-3.3-70b-versatile",temperature=0) |
|
|
| prompt=ChatPromptTemplate.from_template(""" |
| Answer only from the supplied context. |
| Context: |
| {context} |
| |
| Question: |
| {question} |
| """) |
| chain=prompt|llm|StrOutputParser() |
|
|
| def ask(files,question,chunk_size,overlap,k): |
| docs=[] |
| for f in files: |
| docs.extend(PyPDFLoader(f.name).load()) |
| splitter=RecursiveCharacterTextSplitter(chunk_size=int(chunk_size),chunk_overlap=int(overlap)) |
| chunks=splitter.split_documents(docs) |
| db=Chroma.from_documents(chunks,embeddings) |
| retrieved=db.as_retriever(search_kwargs={"k":int(k)}).invoke(question) |
| context="\n\n".join(d.page_content for d in retrieved) |
| answer=chain.invoke({"context":context,"question":question}) |
| sources="\n".join(f"{d.metadata.get('source')} | Page {d.metadata.get('page')}" for d in retrieved) |
| return answer,sources |
|
|
| gr.Interface( |
| fn=ask, |
| inputs=[ |
| gr.File(file_count="multiple",file_types=[".pdf"]), |
| gr.Textbox(label="Question"), |
| gr.Slider(300,1500,value=800), |
| gr.Slider(0,300,value=150), |
| gr.Slider(1,10,value=4,step=1) |
| ], |
| outputs=[gr.Textbox(label="Answer"),gr.Textbox(label="Sources")], |
| title="Document QA using Groq").launch() |
|
|
