Spaces:
Runtime error
Runtime error
File size: 3,316 Bytes
318c41e 48b048a 6856401 48b048a 6856401 48b048a 318c41e 48b048a 36625c3 48b048a |
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 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 |
from langchain_community.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.embeddings import SentenceTransformerEmbeddings
from langchain_community.vectorstores import Chroma
from langchain_community.llms import LlamaCpp
from langchain.chains import RetrievalQA
from langchain.schema.runnable import RunnablePassthrough
from langchain.schema.output_parser import StrOutputParser
from langchain.prompts import ChatPromptTemplate
from langchain_huggingface import HuggingFaceEmbeddings
import gradio as gr
import os
# Set your Hugging Face API key
os.environ['HF_API_KEY']
api_key = os.getenv('HF_API_KEY')
if api_key is None:
raise ValueError("Hugging Face API key is not set. Please set it in your environment.")
# Load documents from a directory
loader = PyPDFLoader("healthyheart.pdf")
docs = loader.load()
# Split documents into chunks
text_splitter = RecursiveCharacterTextSplitter(chunk_size=300, chunk_overlap=50)
chunks = text_splitter.split_documents(docs)
# Create embeddings and vector store
embeddings = SentenceTransformerEmbeddings(model_name="NeuML/pubmedbert-base-embeddings")
vectorstore = Chroma.from_documents(chunks, embeddings)
# Create a retriever
retriever = vectorstore.as_retriever(search_kwargs={'k': 5})
# Load the LLM (LlamaCpp)
llm = LlamaCpp(
model_path='/models/MaziyarPanahi/BioMistral-7B-GGUF',
temperature=0.2,
max_tokens=2048,
top_p=1
)
# Define the prompt template
template = """
You are a Medical Assistant that follows the instructions and generates accurate responses based on the query and the context provided. Please be truthful and give direct answers.
{query}
"""
prompt = ChatPromptTemplate.from_template(template)
# Create the retrieval chain
retrieval_chain = (
{"context": retriever, "query": RunnablePassthrough()}
| prompt
| llm
| StrOutputParser()
)
# Define the chat function for Gradio
def chat(user_input):
if user_input.lower() == 'exit':
return "Exiting..."
if not user_input.strip():
return "Please enter a valid query."
result = retrieval_chain.invoke(user_input)
return result
# Create Gradio interface with improved design
iface = gr.Interface(
fn=chat,
inputs=gr.Textbox(label="Your Query", placeholder="Type your question here...", lines=2),
outputs=gr.Textbox(label="Response"),
title="🩺 BioMistral Medical Chatbot",
description="🤖 Ask me any healthcare or biology-related queries!",
theme="soft",
live=True,
css="""
body {
background-color: #f0f4f8;
color: #333;
}
.gradio-container {
border-radius: 12px;
box-shadow: 0px 4px 10px rgba(0, 0, 0, 0.1);
background: #ffffff;
padding: 20px;
}
input, textarea {
border-radius: 8px;
border: 1px solid #ddd;
padding: 10px;
}
button {
background-color: #007bff;
color: white;
border-radius: 8px;
padding: 10px 15px;
border: none;
transition: 0.3s;
}
button:hover {
background-color: #0056b3;
}
"""
)
# Launch the Gradio app
iface.launch() |