Update app.py

app.py

@@ -1,64 +1,78 @@
 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)",
-        ),
-    ],
+from langchain.chains import create_retrieval_chain
+from langchain.vectorstores import Chroma
+from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+from langchain.memory.chat_message_histories import ChatMessageHistory
+from langchain_openai import ChatOpenAI
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain.embeddings import HuggingFaceEmbeddings
+
+embedding_model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+
+persist_directory = 'vec_db'
+
+vectordb = Chroma(persist_directory=persist_directory,
+                           embedding_function=embedding_model)
+
+vectordb_retriever = vectordb.as_retriever(search_kwargs={'k':5})
+
+llm = ChatOpenAI(model="gpt-4.1-nano", temperature=0.7)
+
+with open("instructions.txt", 'r') as file:
+    instructions = file.read()
+
+
+# Custom prompt
+custom_prompt = ChatPromptTemplate.from_messages([
+    ("system", instructions),
+    MessagesPlaceholder(variable_name="chat_history"),
+    ("user", "Question: {input}\nContext: {context}")
+])
+
+# Memory
+memory = ConversationBufferMemory(
+    memory_key="chat_history",
+    return_messages=True
 )
 
+question_answer_chain = create_stuff_documents_chain(llm, custom_prompt)
+
+chain = create_retrieval_chain(vectordb_retriever, question_answer_chain)
+
+def conversate_assistant(query, history):
+    greetings = {"hey", "hi", "hello"}
+    normalized_query = query.strip().lower()
+
+    if len(memory.load_memory_variables({})["chat_history"]) >=6:
+        chat_history = memory.load_memory_variables({})["chat_history"][-6::]
+    else:
+        chat_history = memory.load_memory_variables({})["chat_history"]
+
+    # If greeting, skip retrieval and context
+    if normalized_query in greetings:
+        response = question_answer_chain.invoke({
+            "input": query,
+            "context": [],  # empty context for greetings
+            "chat_history": chat_history
+        })
+        answer = response
+    else:
+        response = chain.invoke({
+            "input": query,
+            "chat_history": chat_history
+        })
+        answer = response['answer']
+    
+    # Save to memory
+    memory.save_context({"input": query}, {"output": answer})
+
+    return answer
+
+demo = gr.ChatInterface(
+    conversate_assistant,
+    type="messages"
+)
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()