update app.py

app.py

@@ -1,63 +1,101 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+from langchain.prompts import PromptTemplate
+from langchain.embeddings import SentenceTransformerEmbeddings
+
+# Set model_kwargs with trust_remote_code=True
+embeddings = SentenceTransformerEmbeddings(
+    model_name="nomic-ai/nomic-embed-text-v1.5",
+    model_kwargs={"trust_remote_code": True}
+)
+
+from langchain_community.vectorstores import FAISS
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain.document_loaders import TextLoader, PyPDFLoader
+
+loader = PyPDFLoader("https://www.versusarthritis.org/media/24901/fibromyalgia-information-booklet-july2021.pdf")
+documents = loader.load()
+
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+docs = text_splitter.split_documents(documents)
+vector_store = FAISS.from_documents(docs, embeddings)
+retriever = vector_store.as_retriever()
+
+from langchain import hub
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.runnables import RunnablePassthrough
+
+prompt = hub.pull("rlm/rag-prompt")
+
+from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("mohamedalcafory/PubMed_Llama3.1_Based_model")
+model = AutoModelForCausalLM.from_pretrained("mohamedalcafory/PubMed_Llama3.1_Based_model")
+
+from transformers import pipeline
+from langchain_huggingface import HuggingFacePipeline
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=512,
+    temperature=0.7,
+    top_p=0.95,
+    repetition_penalty=1.15
+)
+
+llm = HuggingFacePipeline(pipeline=pipe)
+
+prompt = PromptTemplate(
+    input_variables=["query"],
+    template="{query}"
+)
+
+# Define the retrieval chain
+retrieve_docs = (lambda x: retriever.get_relevant_documents(x["query"]))
+
+# Define the generator chain
+generator_chain = (
+    prompt
+    | llm
+    | StrOutputParser()
 )
 
+def format_docs(docs):
+    # Check if docs is a list of Document objects or just strings
+    if docs and hasattr(docs[0], 'page_content'):
+        return "\n\n".join(doc.page_content for doc in docs)
+    else:
+        return "\n\n".join(str(doc) for doc in docs)
+
+# Create the full RAG chain
+rag_chain = (
+    RunnablePassthrough.assign(context=retrieve_docs)
+    | RunnablePassthrough.assign(
+        formatted_context=lambda x: format_docs(x["context"])
+    )
+    | prompt
+    | llm
+    | StrOutputParser()
+)
+
+def process_query(query):
+    try:
+        response = rag_chain.invoke({"query": query})
+        return response
+    except Exception as e:
+        return f"An error occurred: {str(e)}"
+
+# Create Gradio interface
+demo = gr.Interface(
+    fn=process_query,
+    inputs=gr.Textbox(label= "Your question", lines=2, placeholder="Enter your question here..."),
+    outputs=gr.Textbox(label="Response"),
+    title="Fibromyalgia Q&A Assistant",
+    description="Ask questions and get answers based on the retrieved context.",
+    examples=[
+        ["How does Physiotherapy work with Fibromyalgia?"],
+        ["What are the common treatments for chronic pain?"],
+    ]
+)
 
 if __name__ == "__main__":
     demo.launch()