Update app.py

app.py

@@ -1,64 +1,114 @@
+Hugging Face's logo
+Hugging Face
+Models
+Datasets
+Spaces
+Community
+Docs
+Enterprise
+Pricing
+
+
+
+Spaces:
+
+jawad2412
+/
+ClickMediaLabInc_chatbot
+
+
+like
+0
+
+Logs
+App
+Files
+Community
+Settings
+ClickMediaLabInc_chatbot
+/
+chatbot.py
+
+jawad2412's picture
+jawad2412
+Upload 3 files
+1f289e4
+verified
+31 minutes ago
+raw
+
+Copy download link
+history
+blame
+edit
+delete
+
+2.37 kB
+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
-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)",
-        ),
-    ],
-)
 
+# 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__":
-    demo.launch()
+    iface.launch()
+