Create app.py

app.py

@@ -0,0 +1,91 @@
+from google.colab import drive
+drive.mount("/content/drive")
+!pip install langchain sentence-transformers chromadb llama-cpp-python langchain_community pypdf
+from langchain_community.document_loaders import PyPDFDirectoryLoader
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_community.embeddings import SentenceTransformerEmbeddings
+from langchain.vectorstores import Chroma
+from langchain_community.llms import LlamaCpp
+from langchain.chains import RetrievalQA, LLMChain
+loader=PyPDFDirectoryLoader("/content/drive/MyDrive/BioMistral/Data")
+docs=loader.load()
+text_splitter=RecursiveCharacterTextSplitter(chunk_size=300, chunk_overlap=50)
+chunks=text_splitter.split_documents(docs)
+import os
+import os
+os.environ["HUGGINGFACEHUB_API_TOKEN"] = os.getenv("HUGGINGFACEHUB_API_TOKEN")
+
+embeddings = SentenceTransformerEmbeddings(model_name="NeuML/pubmedbert-base-embeddings")
+vectorstore = Chroma.from_documents(chunks, embeddings)
+query="What are the major risk factors of heart disease?"
+search_results=vectorstore.similarity_search(query)
+search_results
+retriever=vectorstore.as_retriever(search_kwargs={"k":5})
+retriever.get_relevant_documents(query)
+llm=LlamaCpp(
+    model_path="/content/drive/MyDrive/BioMistral/BioMistral-7B.Q4_K_M.gguf",
+    temperature=0.2,
+    max_tokens=2048,
+    top_p=1
+)
+template="""
+<|context|>
+You are an Medical Assistant that follows the instruction and generate the accurate response based on the query and the context provided.
+Please be truthful and give direct answers.
+</s>
+<|user|>
+{query}
+</s>
+<|assistant|>
+"""
+from langchain.schema.runnable import RunnablePassthrough
+from langchain.schema.output_parser import StrOutputParser
+from langchain.prompts import ChatPromptTemplate
+prompt=ChatPromptTemplate.from_template(template)
+rag_chain=(
+    {"context":retriever,"query":RunnablePassthrough()}
+    | prompt
+    | llm
+    | StrOutputParser()
+  )
+response=rag_chain.invoke("query")
+response
+import sys
+while True:
+  user_input=input(f"Input query: ")
+  if user_input=='exit':
+    print("Exiting...")
+    sys.exit()
+  if user_input=="":
+    continue
+  result=rag_chain.invoke(user_input)
+  print("Answer: ",result)
+!pip install gradio
+import gradio as gr
+
+# Define a function to handle queries
+def chatbot_ui(user_query):
+    if not user_query.strip():
+        return "Please enter a valid query."
+    try:
+        result = rag_chain.invoke(user_query)
+        return result
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+# Create the Gradio interface
+interface = gr.Interface(
+    fn=chatbot_ui,  # Function to process the query
+    inputs=gr.Textbox(label="Enter your medical query:", placeholder="Ask a medical question here..."),
+    outputs=gr.Textbox(label="Chatbot Response"),
+    title="Medical Assistant Chatbot",
+    description="A chatbot made for heart patients.",
+    examples=[
+        ["What are the symptoms of diabetes?"],
+        ["Explain the risk factors of heart disease."],
+        ["How can I reduce cholesterol levels naturally?"],
+    ]
+)
+
+# Launch the Gradio interface
+interface.launch(share=True)