Spaces:
Build error
Build error
File size: 2,369 Bytes
1f289e4 |
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 |
import os
from langchain_community.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.vectorstores import FAISS
from langchain_huggingface import HuggingFaceEmbeddings
from langchain.chains import RetrievalQA
from langchain.prompts import PromptTemplate
from langchain_groq import ChatGroq
import gradio as gr
# Load Groq API key from env variables
groq_api_key = os.getenv("GROQ_API_KEY")
def load_and_index_pdf(pdf_path="company_data.pdf"):
loader = PyPDFLoader(pdf_path)
documents = loader.load()
splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
texts = splitter.split_documents(documents)
embedding = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
db = FAISS.from_documents(texts, embedding)
db.save_local("company_faiss_index")
def setup_qa():
embedding = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
if not os.path.exists("company_faiss_index"):
load_and_index_pdf()
db = FAISS.load_local("company_faiss_index", embedding, allow_dangerous_deserialization=True)
retriever = db.as_retriever(search_type="similarity", search_kwargs={"k": 3})
llm = ChatGroq(model_name="llama3-70b-8192", api_key=groq_api_key)
prompt = PromptTemplate.from_template("""
You are a helpful assistant for a digital marketing company.
Try to answer the user's question based on the provided context from the company document.
If the answer is not found in the context, provide a helpful and accurate answer from your own knowledge, focusing on digital marketing topics.
Context:
{context}
Question:
{question}
""")
qa_chain = RetrievalQA.from_chain_type(
llm=llm,
retriever=retriever,
return_source_documents=False,
chain_type_kwargs={"prompt": prompt}
)
return qa_chain
qa_chain = setup_qa()
def answer_question(query):
result = qa_chain.invoke(query)
return result['result']
# Minimal Gradio UI
iface = gr.Interface(
fn=answer_question,
inputs=gr.Textbox(lines=2, placeholder="Ask a question about digital marketing..."),
outputs="text",
title="CLick Media Lab Chatbot"
)
if __name__ == "__main__":
iface.launch()
|