Update app.py

app.py

@@ -1,64 +1,131 @@
+import os
+import pandas as pd
 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")
+###################################
+# 1. Load and Chunk CSV Data
+###################################
+df = pd.read_csv("datasets.csv")
 
+# We will chunk the rows in groups of 1,000
+chunk_size = 1000
+context_data = []
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+for start_index in range(0, len(df), chunk_size):
+    # Collect rows for one chunk
+    chunk_rows = df.iloc[start_index : start_index + chunk_size]
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    # Build a single text block for these rows
+    text_block = ""
+    for row_idx in range(len(chunk_rows)):
+        row_data = chunk_rows.iloc[row_idx]
+        for col_name in df.columns:
+            text_block += f"{col_name}: {str(row_data[col_name])} "
+        text_block += "\n"  # separate rows for clarity
 
-    messages.append({"role": "user", "content": message})
+    context_data.append(text_block)
 
-    response = ""
+###################################
+# 2. Retrieve API Key
+###################################
+groq_key = os.environ.get('groq_api_keys')
 
-    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
+###################################
+# 3. Language Model & Embeddings
+###################################
+from langchain_groq import ChatGroq
+llm = ChatGroq(
+    model="llama-3.1-70b-versatile",
+    api_key=groq_key
+)
 
-        response += token
-        yield response
+from langchain_huggingface import HuggingFaceEmbeddings
+embed_model = HuggingFaceEmbeddings(
+    model_name="mixedbread-ai/mxbai-embed-large-v1"
+)
 
+###################################
+# 4. Vector Store
+###################################
+from langchain_chroma import Chroma
 
+vectorstore = Chroma(
+    collection_name="professional_medical_store",
+    embedding_function=embed_model,
+    persist_directory="./",
+)
+
+# Add chunked data to the vector store
+vectorstore.add_texts(context_data)
+retriever = vectorstore.as_retriever()
+
+###################################
+# 5. Prompt Configuration
+###################################
+from langchain_core.prompts import PromptTemplate
+from langchain_core.runnables import RunnablePassthrough
+from langchain_core.output_parsers import StrOutputParser
+
+prompt_template = """
+You are a supportive and professional mental-health consultant with extensive medical knowledge.
+Speak compassionately while maintaining a calm, informative tone.
+Use the context to answer questions about mental well-being or related medical considerations.
+If you do not know the answer, say so without hesitation.
+Focus on providing actionable insights without explicitly mentioning the context.
+Always encourage users to seek professional or emergency help where appropriate.
+
+Context: {context}
+Question: {question}
+Answer:
 """
-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)",
-        ),
-    ],
+
+rag_prompt = PromptTemplate.from_template(prompt_template)
+
+rag_chain = (
+    {"context": retriever, "question": RunnablePassthrough()}
+    | rag_prompt
+    | llm
+    | StrOutputParser()
 )
 
+###################################
+# 6. Gradio Interface
+###################################
+def chain_stream(user_input):
+    partial_text = ""
+    for new_text in rag_chain.stream(user_input):
+        partial_text += new_text
+        yield partial_text
+
+examples = [
+    "I have been feeling anxious and unable to focus. Any recommendations?",
+    "I've been feeling extremely tired lately—should I see a professional?"
+]
+
+disclaimer = (
+    "**Disclaimer**: I am an AI language model and not a licensed healthcare professional. "
+    "For urgent concerns, please seek immediate help from qualified medical professionals."
+)
+
+title = "Professional Mental Health & Medical Assistant"
+
+demo = gr.Interface(
+    fn=chain_stream,
+    inputs=gr.Textbox(
+        lines=3,
+        placeholder="Ask your question or describe your situation here..."
+    ),
+    outputs="text",
+    title=title,
+    description=(
+        "Welcome to your mental-health and medical information companion. "
+        "I provide professional, empathetic, and trustworthy guidance. "
+        "Please remember this is not a substitute for direct professional consultation."
+    ),
+    article=disclaimer,
+    examples=examples,
+    allow_flagging="never",
+)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(server_name="0.0.0.0", server_port=7860)