Create streamlit_app.py

streamlit_app.py

@@ -0,0 +1,132 @@
+# streamlit_app.py
+# A minimal Streamlit app rebuilt with the LangChain framework.
+
+import streamlit as st
+import torch
+from transformers import pipeline
+
+# Updated LangChain imports for modern versions
+from langchain_community.llms import HuggingFacePipeline
+from langchain.prompts import PromptTemplate
+from langchain.chains import LLMChain
+from langchain.memory import ConversationBufferMemory
+
+# -----------------------------------------------------------------------------
+# CORE MODEL LOGIC (Rebuilt with LangChain)
+# -----------------------------------------------------------------------------
+class LangChainBot:
+    def __init__(self):
+        """
+        Loads the models and wraps them in LangChain components.
+        """
+        try:
+            # 1. Load the base Hugging Face pipelines
+            generator_pipeline = pipeline(
+                "text2text-generation",
+                model="ai4bharat/IndicBARTSS",
+                device=0 if torch.cuda.is_available() else -1,
+                torch_dtype=(torch.float16 if torch.cuda.is_available() else torch.float32),
+                max_new_tokens=150,
+                repetition_penalty=1.2
+            )
+            
+            # Added `trust_remote_code=True` to allow the special translator model to load.
+            self.translator = pipeline(
+                "translation",
+                model="ai4bharat/indictrans2-indic-indic-1B",
+                device=0 if torch.cuda.is_available() else -1,
+                trust_remote_code=True
+            )
+
+            # 2. Wrap the generator in a LangChain LLM object
+            llm = HuggingFacePipeline(pipeline=generator_pipeline)
+
+            # 3. Create a Prompt Template
+            template = """
+            You are a helpful conversational AI. Respond to the user's message.
+
+            {history}
+            मनुष्य: {input}
+            सहायक:
+            """
+            prompt_template = PromptTemplate(input_variables=["history", "input"], template=template)
+
+            # 4. Set up conversational memory
+            self.memory = ConversationBufferMemory(memory_key="history")
+
+            # 5. Create the final LLMChain
+            self.chain = LLMChain(
+                llm=llm,
+                prompt=prompt_template,
+                verbose=True,
+                memory=self.memory
+            )
+            
+        except Exception as e:
+            st.error(f"Fatal: Could not load models. Error: {e}")
+            self.chain = None
+            self.translator = None
+
+    def _translate(self, text, source_lang, target_lang):
+        """Translation logic remains the same."""
+        if not self.translator or source_lang == target_lang:
+            return text
+        try:
+            codes = {'english': 'eng_Latn', 'hindi': 'hin_Deva', 'tamil': 'tam_Taml', 'telugu': 'tel_Telu'}
+            result = self.translator(text, src_lang=codes[source_lang], tgt_lang=codes[target_lang])
+            return result[0]['translation_text']
+        except Exception as e:
+            st.warning(f"Translation failed. Error: {e}")
+            return text
+
+    def get_response(self, user_message, input_lang, output_lang):
+        """The main function to get a response."""
+        if not self.chain:
+            return "Error: The LangChain chain is not initialized."
+
+        hindi_message = self._translate(user_message, input_lang, 'hindi')
+        hindi_response = self.chain.run(hindi_message)
+        final_response = self._translate(hindi_response, 'hindi', output_lang)
+
+        return final_response
+
+# -----------------------------------------------------------------------------
+# MINIMAL STREAMLIT UI (This part remains mostly the same)
+# -----------------------------------------------------------------------------
+
+st.set_page_config(layout="centered")
+st.title("LangChain Model Interface")
+
+@st.cache_resource
+def load_bot():
+    return LangChainBot()
+
+bot = load_bot()
+
+if bot and bot.chain: # Only show the UI if the bot loaded successfully
+    st.markdown("---")
+    language_options = ["english", "hindi", "tamil", "telugu"]
+    col1, col2 = st.columns(2)
+    with col1:
+        input_lang = st.selectbox("Input Language", options=language_options, index=0)
+    with col2:
+        output_lang = st.selectbox("Output Language", options=language_options, index=1)
+
+    user_input = st.text_area("Your Message:", height=100)
+
+    if st.button("Get Response"):
+        if user_input:
+            with st.spinner("LangChain is processing your request..."):
+                response = bot.get_response(user_input, input_lang, output_lang)
+                st.markdown("### Model Response:")
+                st.info(response)
+        else:
+            st.warning("Please enter a message.")
+
+    # Add a button to clear LangChain's memory
+    if st.button("Clear Conversation Memory"):
+        if hasattr(bot, 'memory'):
+            bot.memory.clear()
+            st.success("Conversation memory has been cleared.")
+else:
+    st.error("Application could not start. Please check the logs.")