initial commit

README.md

@@ -1,5 +1,5 @@
 ---
-title: Gradio Chatbot
+title: ElloraAI 2.0
 emoji: 💬
 colorFrom: yellow
 colorTo: purple
@@ -7,6 +7,7 @@ sdk: gradio
 sdk_version: 5.0.1
 app_file: app.py
 pinned: false
+license: apache-2.0
 ---
 
 An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).

app.py

@@ -1,64 +1,83 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+from langchain.llms import HuggingFacePipeline
+from langchain.prompts import PromptTemplate
+from langchain.chains import ConversationChain
+from langchain.memory import ConversationBufferMemory
+import torch
 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")
+# Load the model and tokenizer
+model_name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="cpu")
+model = model.to(device)
 
+# Create a Hugging Face pipeline
+hf_pipeline = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    device_map="cpu",
+    max_new_tokens=500,    # Maximum number of tokens to generate
+    truncation=True,      # Truncate input if it exceeds max_length
+    temperature=1.0,      # Adjust this value based on your use case
+    return_full_text=False,  # Do not include the input prompt in the output
+)
 
-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]})
+# Wrap the pipeline in LangChain
+llm = HuggingFacePipeline(pipeline=hf_pipeline)
 
-    messages.append({"role": "user", "content": message})
+# Define the system-level prompt template
+template = """You are a helpful AI assistant and your name is Ellora mady by Abhishek sharma. Answer the user's questions clearly and concisely.
 
-    response = ""
+Conversation History:
+{history}
 
-    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
+User: {input}
+Assistant:"""
 
-        response += token
-        yield response
+# Create the PromptTemplate
+prompt = PromptTemplate(input_variables=["history", "input"], template=template)
 
+# Add memory for conversation history
+memory = ConversationBufferMemory()
 
-"""
-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)",
-        ),
-    ],
+# Create a chatbot chain
+chatbot = ConversationChain(
+    llm=llm,
+    prompt=prompt,
+    memory=memory,
+    verbose=False  # Set to True to see the prompt and memory in action
 )
 
+# Function to handle chatbot interaction
+def chat(input_text):
+    response = chatbot.run(input_text)
+    return response
+# Create a Gradio interface
+def gradio_chat(input_text, history):
+    if input_text.lower() == "exit":
+        return "Chat ended."
+    response = chat(input_text)
+    history.append((input_text, response))
+    return history, history  # Return updated history
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("## Ellora AI by Abhishek sharma")
+    chatbot_interface = gr.Chatbot(label="Chat History")
+    user_input = gr.Textbox(label="Your Question")
+    submit_button = gr.Button("Send")
+    clear_button = gr.Button("Clear")
+
+    # Define the interaction
+    submit_button.click(
+        gradio_chat,
+        inputs=[user_input, chatbot_interface],
+        outputs=[chatbot_interface, chatbot_interface]
+    )
+    clear_button.click(lambda: [], None, chatbot_interface, queue=False)
 
-if __name__ == "__main__":
-    demo.launch()
+# Launch the Gradio app
+demo.launch(pwa=True,share=True)

requirements.txt

@@ -1 +0,0 @@
-huggingface_hub==0.25.2