Update app.py

app.py

@@ -1,64 +1,80 @@
+import os
+import pandas as pd
+import google.generativeai as genai
+import numpy as np
 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")
+# Initialize an empty DataFrame with columns 'Title' and 'Text'
+df = pd.DataFrame(columns=['Title', 'Text'])
 
+# Mapping filenames to custom titles
+title_mapping = {
+    'company.txt': 'company_data',
+    'products.txt': 'product_data',
+    'shipping.txt': 'shipping_data'
+}
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Loop through each file in the current directory and process the relevant ones
+for file_name in os.listdir('.'):
+    if file_name in title_mapping:
+        try:
+            with open(file_name, 'r', encoding='utf-8') as file:
+                text = file.read().replace('\n', ' ')  # Replace newlines with spaces for cleaner text
+                custom_title = title_mapping[file_name]
+                new_row = pd.DataFrame({'Title': [custom_title], 'Text': [text]})
+                df = pd.concat([df, new_row], ignore_index=True)
+        except Exception as e:
+            print(f"Error processing file {file_name}: {e}")
 
-    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})
+    GEMINI_API_KEY = os.getenv("GOOGLE_API_KEY")
+    if not GEMINI_API_KEY:
+        return "Error: Gemini API key not found. Please set the GEMINI_API_KEY environment variable."
 
-    response = ""
+    # Configure the Gemini API
+    try:
+        genai.configure(api_key=GEMINI_API_KEY)
+    except Exception as e:
+        return f"Error: Failed to configure the Gemini API. Details: {e}"
 
-    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
+# Function to embed text using the Google Generative AI API
+def embed_text(text):
+    return genai.embed_content(model='models/embedding-001', content=text, task_type='retrieval_document')['embedding']
 
-        response += token
-        yield response
+# Embed the text and ensure embeddings are stored in the DataFrame
+if 'Embeddings' not in df.columns:
+    df['Embeddings'] = df['Text'].apply(embed_text)
 
+# Function to calculate similarity score between the query and document embeddings
+def query_similarity_score(query, vector):
+    query_embedding = embed_text(query)
+    return np.dot(query_embedding, vector)
 
-"""
-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)",
-        ),
+# Function to get the most similar document based on the query
+def most_similar_document(query):
+    # Create a local DataFrame copy to store similarity scores
+    local_df = df.copy()
+    # Calculate similarity for all rows
+    local_df['Similarity'] = local_df['Embeddings'].apply(lambda vector: query_similarity_score(query, vector))
+    # Sort by similarity score and retrieve the top match
+    most_similar = local_df.sort_values('Similarity', ascending=False).iloc[0]
+    return most_similar['Title'], most_similar['Text']
+
+# Function to generate a response using the RAG approach
+def RAG(query):
+    title, text = most_similar_document(query)
+    model = genai.GenerativeModel('gemini-pro')
+    prompt = f"Answer this query:\n{query}.\nOnly use this context to answer:\n{text}"
+    response = model.generate_content(prompt)
+    return f"{response.text}\n\nSource Document: {title}" 
+
+iface = gr.Interface(
+    fn=RAG,  # Main function to handle the query
+    inputs=[
+        gr.Textbox(label="Enter Your Query"),  # Input for the user's query
     ],
+    outputs=gr.Textbox(label="Response"),  # Output for the generated response
+    title="Patrick's Multilingual Query Handler"
 )
 
 
-if __name__ == "__main__":
-    demo.launch()