Update app.py

app.py

@@ -1,64 +1,71 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+from huggingface_hub import hf_hub_download
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import Chroma
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_groq import ChatGroq
+from langchain.document_loaders import PyPDFLoader
 
-"""
-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")
+# --- Hugging Face Hub Setup ---
+HF_REPO_ID = "Shami96/7solar_documentation"  # Replace with your dataset
+HF_PDF_NAME = "7solar_documentation.pdf"  # Your PDF filename
 
+# --- Load PDF from Hugging Face Hub ---
+def load_pdf_from_hf():
+    pdf_path = hf_hub_download(
+        repo_id=HF_REPO_ID,
+        filename=HF_PDF_NAME,
+        token=os.environ.get("HF_TOKEN")  # For private repos
+    )
+    loader = PyPDFLoader(pdf_path)
+    return loader.load()
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# --- Split & Embed Docs ---
+def create_vector_db():
+    docs = load_pdf_from_hf()
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=2000,
+        chunk_overlap=300
+    )
+    chunks = text_splitter.split_documents(docs)
+    embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
+    return Chroma.from_documents(chunks, embeddings)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# --- RAG Chatbot Logic ---
+def get_response(query, history):
+    # Handle greetings
+    if query.lower() in ["hi", "hello", "hey"]:
+        return history + [(query, "Hello! 👋 Ask me about 7Solar's solar packages or services!")]
 
-    messages.append({"role": "user", "content": message})
+    # Retrieve relevant doc chunks
+    matching_docs = vector_db.similarity_search(query, k=5)
+    if not matching_docs:
+        return history + [(query, "I couldn't find details. Ask about 7Solar's services!")]
 
-    response = ""
+    # Generate LLM response
+    llm = ChatGroq(
+        model_name="llama3-70b-8192",
+        temperature=0.2,
+        api_key=os.environ.get("GROQ_API_KEY")  # Set in Spaces Secrets
+    )
+    context = "\n\n".join([doc.page_content for doc in matching_docs])
+    response = llm.invoke(
+        f"Answer this query using ONLY the text below:\n\n{context}\n\nQuestion: {query}"
+    )
+    return history + [(query, response.content)]
 
-    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
+# --- Initialize Vector DB ---
+print("⚙️ Loading document...")
+vector_db = create_vector_db()
 
-        response += token
-        yield response
+# --- Gradio Interface ---
+with gr.Blocks() as demo:
+    gr.Markdown("# ☀️ 7Solar Smart Assistant")
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(label="Ask about solar packages, services, etc.")
+    msg.submit(get_response, [msg, chatbot], [chatbot])
+    clear = gr.Button("Clear Chat")
+    clear.click(lambda: [], None, chatbot, queue=False)
 
-
-"""
-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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()