Update app.py

app.py

@@ -51,11 +51,16 @@ def bhashini_translate(text: str, from_code: str = "en", to_code: str = "hi") ->
     response = requests.post(url, json=payload, headers=headers)
     
     if response.status_code != 200:
-        print(f'Error in initial request: {response.status_code}')
+        print(f'Error in initial request: {response.status_code}, Response: {response.text}')
         return {"status_code": response.status_code, "message": "Error in translation request", "translated_content": None}
 
     print('Initial request successful, processing response...')
     response_data = response.json()
+    print('Full response data:', response_data)  # Debug the full response
+    if "pipelineInferenceAPIEndPoint" not in response_data or "callbackUrl" not in response_data["pipelineInferenceAPIEndPoint"]:
+        print('Unexpected response structure:', response_data)
+        return {"status_code": 400, "message": "Unexpected API response structure", "translated_content": None}
+
     service_id = response_data["pipelineResponseConfig"][0]["config"][0]["serviceId"]
     callback_url = response_data["pipelineInferenceAPIEndPoint"]["callbackUrl"]
     
@@ -74,7 +79,7 @@ def bhashini_translate(text: str, from_code: str = "en", to_code: str = "hi") ->
     compute_response = requests.post(callback_url, json=compute_payload, headers=headers2)
     
     if compute_response.status_code != 200:
-        print(f'Error in translation request: {compute_response.status_code}')
+        print(f'Error in translation request: {compute_response.status_code}, Response: {compute_response.text}')
         return {"status_code": compute_response.status_code, "message": "Error in translation", "translated_content": None}
     
     print('Translation request successful, processing translation...')
@@ -264,6 +269,273 @@ with gr.Blocks(title="Science Chatbot", theme='gradio/soft') as demo:
 
 if __name__ == "__main__":
     demo.launch(server_name="0.0.0.0", server_port=7860)# import gradio as gr
+# from phi.agent import Agent
+# from phi.model.groq import Groq
+# import os
+# import logging
+# from sentence_transformers import CrossEncoder
+# from backend.semantic_search import table, retriever
+# import numpy as np
+# from time import perf_counter
+# import requests
+
+# # Set up logging
+# logging.basicConfig(level=logging.INFO)
+# logger = logging.getLogger(__name__)
+
+# # API Key setup
+# api_key = os.getenv("GROQ_API_KEY")
+# if not api_key:
+#     gr.Warning("GROQ_API_KEY not found. Set it in 'Repository secrets'.")
+#     logger.error("GROQ_API_KEY not found.")
+#     api_key = ""  # Fallback to empty string, but this will fail without a key
+# else:
+#     os.environ["GROQ_API_KEY"] = api_key
+
+# # Bhashini API setup
+# bhashini_api_key = os.getenv("API_KEY")
+# bhashini_user_id = os.getenv("USER_ID")
+
+# def bhashini_translate(text: str, from_code: str = "en", to_code: str = "hi") -> dict:
+#     """Translates text from source language to target language using the Bhashini API."""
+#     if not text.strip():
+#         print('Input text is empty. Please provide valid text for translation.')
+#         return {"status_code": 400, "message": "Input text is empty", "translated_content": None}
+#     else:
+#         print('Input text - ', text)
+#     print(f'Starting translation process from {from_code} to {to_code}...')
+#     gr.Warning(f'Translating to {to_code}...')
+    
+#     url = 'https://meity-auth.ulcacontrib.org/ulca/apis/v0/model/getModelsPipeline'
+#     headers = {
+#         "Content-Type": "application/json",
+#         "userID": bhashini_user_id,
+#         "ulcaApiKey": bhashini_api_key
+#     }
+#     payload = {
+#         "pipelineTasks": [{"taskType": "translation", "config": {"language": {"sourceLanguage": from_code, "targetLanguage": to_code}}}],
+#         "pipelineRequestConfig": {"pipelineId": "64392f96daac500b55c543cd"}
+#     }
+    
+#     print('Sending initial request to get the pipeline...')
+#     response = requests.post(url, json=payload, headers=headers)
+    
+#     if response.status_code != 200:
+#         print(f'Error in initial request: {response.status_code}')
+#         return {"status_code": response.status_code, "message": "Error in translation request", "translated_content": None}
+
+#     print('Initial request successful, processing response...')
+#     response_data = response.json()
+#     service_id = response_data["pipelineResponseConfig"][0]["config"][0]["serviceId"]
+#     callback_url = response_data["pipelineInferenceAPIEndPoint"]["callbackUrl"]
+    
+#     print(f'Service ID: {service_id}, Callback URL: {callback_url}')
+    
+#     headers2 = {
+#         "Content-Type": "application/json",
+#         response_data["pipelineInferenceAPIEndPoint"]["inferenceApiKey"]["name"]: response_data["pipelineInferenceAPIEndPoint"]["inferenceApiKey"]["value"]
+#     }
+#     compute_payload = {
+#         "pipelineTasks": [{"taskType": "translation", "config": {"language": {"sourceLanguage": from_code, "targetLanguage": to_code}, "serviceId": service_id}}],
+#         "inputData": {"input": [{"source": text}], "audio": [{"audioContent": None}]}
+#     }
+    
+#     print(f'Sending translation request with text: "{text}"')
+#     compute_response = requests.post(callback_url, json=compute_payload, headers=headers2)
+    
+#     if compute_response.status_code != 200:
+#         print(f'Error in translation request: {compute_response.status_code}')
+#         return {"status_code": compute_response.status_code, "message": "Error in translation", "translated_content": None}
+    
+#     print('Translation request successful, processing translation...')
+#     compute_response_data = compute_response.json()
+#     translated_content = compute_response_data["pipelineResponse"][0]["output"][0]["target"]
+    
+#     print(f'Translation successful. Translated content: "{translated_content}"')
+#     return {"status_code": 200, "message": "Translation successful", "translated_content": translated_content}
+
+# # Initialize PhiData Agent
+# agent = Agent(
+#     name="Science Education Assistant",
+#     role="You are a helpful science tutor for 10th-grade students",
+#     instructions=[
+#         "You are an expert science teacher specializing in 10th-grade curriculum.",
+#         "Provide clear, accurate, and age-appropriate explanations.",
+#         "Use simple language and examples that students can understand.",
+#         "Focus on concepts from physics, chemistry, and biology.",
+#         "Structure responses with headings and bullet points when helpful.",
+#         "Encourage learning and curiosity."
+#     ],
+#     model=Groq(id="llama3-70b-8192", api_key=api_key),
+#     markdown=True
+# )
+
+# # Response Generation Function
+# def retrieve_and_generate_response(query, cross_encoder_choice, history=None):
+#     """Generate response using semantic search and LLM"""
+#     top_rerank = 25
+#     top_k_rank = 20
+    
+#     if not query.strip():
+#         return "Please provide a valid question."
+    
+#     try:
+#         start_time = perf_counter()
+        
+#         # Encode query and search documents
+#         query_vec = retriever.encode(query)
+#         documents = table.search(query_vec, vector_column_name="vector").limit(top_rerank).to_list()
+#         documents = [doc["text"] for doc in documents]
+        
+#         # Re-rank documents using cross-encoder
+#         cross_encoder_model = CrossEncoder('BAAI/bge-reranker-base') if cross_encoder_choice == '(ACCURATE) BGE reranker' else CrossEncoder('cross-encoder/ms-marco-MiniLM-L-6-v2')
+#         query_doc_pair = [[query, doc] for doc in documents]
+#         cross_scores = cross_encoder_model.predict(query_doc_pair)
+#         sim_scores_argsort = list(reversed(np.argsort(cross_scores)))
+#         documents = [documents[idx] for idx in sim_scores_argsort[:top_k_rank]]
+        
+#         # Create context from top documents
+#         context = "\n\n".join(documents[:10]) if documents else ""
+#         context = f"Context information from educational materials:\n{context}\n\n"
+        
+#         # Add conversation history for context
+#         history_context = ""
+#         if history and len(history) > 0:
+#             for user_msg, bot_msg in history[-2:]:  # Last 2 exchanges
+#                 if user_msg and bot_msg:
+#                     history_context += f"Previous Q: {user_msg}\nPrevious A: {bot_msg}\n"
+        
+#         # Create full prompt
+#         full_prompt = f"{history_context}{context}Question: {query}\n\nPlease answer the question using the context provided above. If the context doesn't contain relevant information, use your general knowledge about 10th-grade science topics."
+        
+#         # Generate response
+#         response = agent.run(full_prompt)
+#         response_text = response.content if hasattr(response, 'content') else str(response)
+        
+#         logger.info(f"Response generation took {perf_counter() - start_time:.2f} seconds")
+#         return response_text
+    
+#     except Exception as e:
+#         logger.error(f"Error in response generation: {e}")
+#         return f"Error generating response: {str(e)}"
+
+# def simple_chat_function(message, history, cross_encoder_choice):
+#     """Chat function with semantic search and retriever integration"""
+#     if not message.strip():
+#         return "", history
+    
+#     # Generate response using the semantic search function
+#     response = retrieve_and_generate_response(message, cross_encoder_choice, history)
+    
+#     # Add to history
+#     history.append([message, response])
+    
+#     return "", history
+
+# def translate_text(selected_language, history):
+#     """Translate the last response in history to the selected language."""
+#     iso_language_codes = {
+#         "Hindi": "hi", "Gom": "gom", "Kannada": "kn", "Dogri": "doi", "Bodo": "brx", "Urdu": "ur",
+#         "Tamil": "ta", "Kashmiri": "ks", "Assamese": "as", "Bengali": "bn", "Marathi": "mr",
+#         "Sindhi": "sd", "Maithili": "mai", "Punjabi": "pa", "Malayalam": "ml", "Manipuri": "mni",
+#         "Telugu": "te", "Sanskrit": "sa", "Nepali": "ne", "Santali": "sat", "Gujarati": "gu", "Odia": "or"
+#     }
+    
+#     to_code = iso_language_codes[selected_language]
+#     response_text = history[-1][1] if history and history[-1][1] else ''
+#     print('response_text for translation', response_text)
+#     translation = bhashini_translate(response_text, to_code=to_code)
+#     return translation.get('translated_content', 'Translation failed.')
+
+# # Gradio Interface with layout template
+# with gr.Blocks(title="Science Chatbot", theme='gradio/soft') as demo:
+#     # Header section
+#     with gr.Row():
+#         with gr.Column(scale=10):
+#             gr.HTML(value="""<div style="color: #FF4500;"><h1>Welcome! I am your friend!</h1>Ask me !I will help you<h1><span style="color: #008000">I AM A CHATBOT FOR 10TH SCIENCE WITH TRANSLATION IN 22 LANGUAGES</span></h1></div>""")
+#             gr.HTML(value=f"""<p style="font-family: sans-serif; font-size: 16px;">A free chat bot developed by K.M.RAMYASRI,TGT,GHS.SUTHUKENY using Open source LLMs for 10 std students</p>""")
+#             gr.HTML(value=f"""<p style="font-family: Arial, sans-serif; font-size: 14px;"> Suggestions may be sent to <a href="mailto:ramyasriraman2019@gmail.com" style="color: #00008B; font-style: italic;">ramyadevi1607@yahoo.com</a>.</p>""")
+#         with gr.Column(scale=3):
+#             try:
+#                 gr.Image(value='logo.png', height=200, width=200)
+#             except:
+#                 gr.HTML("<div style='height: 200px; width: 200px; background-color: #f0f0f0; display: flex; align-items: center; justify-content: center;'>Logo</div>")
+
+#     # Chat and input components
+#     chatbot = gr.Chatbot(
+#         [],
+#         elem_id="chatbot",
+#         avatar_images=('https://aui.atlassian.com/aui/8.8/docs/images/avatar-person.svg',
+#                        'https://huggingface.co/datasets/huggingface/brand-assets/resolve/main/hf-logo.svg'),
+#         bubble_full_width=False,
+#         show_copy_button=True,
+#         show_share_button=True,
+#     )
+
+#     with gr.Row():
+#         msg = gr.Textbox(
+#             scale=3,
+#             show_label=False,
+#             placeholder="Enter text and press enter",
+#             container=False,
+#         )
+#         submit_btn = gr.Button(value="Submit text", scale=1, variant="primary")
+
+#     # Additional controls
+#     cross_encoder = gr.Radio(
+#         choices=['(FAST) MiniLM-L6v2', '(ACCURATE) BGE reranker'],
+#         value='(ACCURATE) BGE reranker',
+#         label="Embeddings Model",
+#         info="Select the model for document ranking"
+#     )
+#     language_dropdown = gr.Dropdown(
+#         choices=[
+#             "Hindi", "Gom", "Kannada", "Dogri", "Bodo", "Urdu", "Tamil", "Kashmiri", "Assamese", "Bengali", "Marathi",
+#             "Sindhi", "Maithili", "Punjabi", "Malayalam", "Manipuri", "Telugu", "Sanskrit", "Nepali", "Santali",
+#             "Gujarati", "Odia"
+#         ],
+#         value="Hindi",
+#         label="Select Language for Translation"
+#     )
+#     translated_textbox = gr.Textbox(label="Translated Response")
+
+#     # Event handlers
+#     def update_chat_and_translate(message, history, cross_encoder_choice, selected_language):
+#         if not message.strip():
+#             return "", history, ""
+        
+#         # Generate response
+#         response = retrieve_and_generate_response(message, cross_encoder_choice, history)
+#         history.append([message, response])
+        
+#         # Translate response
+#         translated_text = translate_text(selected_language, history)
+        
+#         return "", history, translated_text
+
+#     msg.submit(update_chat_and_translate, [msg, chatbot, cross_encoder, language_dropdown], [msg, chatbot, translated_textbox])
+#     submit_btn.click(update_chat_and_translate, [msg, chatbot, cross_encoder, language_dropdown], [msg, chatbot, translated_textbox])
+
+#     clear = gr.Button("Clear Conversation")
+#     clear.click(lambda: ([], "", ""), outputs=[chatbot, msg, translated_textbox])
+
+#     # Example questions
+#     gr.Examples(
+#         examples=[
+#             'What is the difference between metals and non-metals?',
+#             'What is an ionic bond?',
+#             'Explain asexual reproduction',
+#             'What is photosynthesis?',
+#             'Explain Newton\'s laws of motion'
+#         ],
+#         inputs=msg,
+#         label="Try these example questions:"
+#     )
+
+# if __name__ == "__main__":
+#     demo.launch(server_name="0.0.0.0", server_port=7860)# import gradio as gr
+
+
 # from phi.agent import Agent
 # from phi.model.groq import Groq
 # import os