Spaces:
Runtime error
Runtime error
File size: 2,530 Bytes
3884e17 dd729e7 3884e17 dd729e7 3884e17 dd729e7 3884e17 dd729e7 3884e17 dd729e7 3884e17 dd729e7 3884e17 dd729e7 3884e17 dd729e7 3884e17 dd729e7 fd0698d 3884e17 fd0698d 3884e17 dd729e7 |
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 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 |
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import FAISS
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.document_loaders import PyMuPDFLoader
from langchain.chains import RetrievalQA
from langchain.llms.base import LLM
from groq import Groq
from typing import List, Optional
import os
import gradio as gr
class GroqLLM(LLM):
model: str = "llama3-8b-8192"
api_key: str = "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"
temperature: float = 0.0
def _call(self, prompt: str, stop: Optional[List[str]] = None) -> str:
client = Groq(api_key=self.api_key)
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": prompt}
]
response = client.chat.completions.create(
model=self.model,
messages=messages,
temperature=self.temperature,
)
return response.choices[0].message.content
@property
def _llm_type(self) -> str:
return "groq-llm"
def process_pdf(pdf_path):
loader = PyMuPDFLoader(pdf_path)
documents = loader.load()
splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
chunks = splitter.split_documents(documents)
embedding = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
vectorstore = FAISS.from_documents(chunks, embedding)
retriever = vectorstore.as_retriever()
llm = GroqLLM(api_key="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")
qa = RetrievalQA.from_chain_type(
llm=llm,
retriever=retriever,
return_source_documents=True
)
return qa
qa_chain = None
def upload_file(file):
global qa_chain
qa_chain = process_pdf(file.name)
return "PDF processed! You can now ask questions."
def ask_question(query):
if qa_chain is None:
return "Please upload a PDF first."
result = qa_chain({"query": query})
return result["result"]
with gr.Blocks() as demo:
gr.Markdown("# 🧠 PDF Q&A with GROQ + LangChain")
with gr.Row():
uploader = gr.File(label="Upload your PDF")
status = gr.Textbox(label="Status")
uploader.change(fn=upload_file, inputs=uploader, outputs=status)
question = gr.Textbox(label="Ask a question")
answer = gr.Textbox(label="Answer")
question.submit(fn=ask_question, inputs=question, outputs=answer)
demo.launch(share=True)
|