Add the model

README.md

@@ -1,11 +1,13 @@
----
-title: CodingSensei
-emoji: 💬
-colorFrom: yellow
-colorTo: purple
-sdk: gradio
-app_file: app.py
-pinned: false
----
-
-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).
+# Code Assistant
+
+A multi-programming code assistant using CodeLlama (LLAMA2) and Gradio.
+
+## How to use
+
+- Enter your code in the input box.
+- The assistant will generate and display the code output.
+
+## Dependencies
+
+- gradio
+- langchain

app.py

@@ -1,63 +1,40 @@
-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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+import requests
+import json
+import gradio as gr
+
+url="http://localhost:11434/api/generate"
+
+headers={
+
+    'Content-Type':'application/json'
+}
+
+history=[]
+
+def generate_response(prompt):
+    history.append(prompt)
+    final_prompt="\n".join(history)
+
+    data={
+        "model":"codingsensei",
+        "prompt":final_prompt,
+        "stream":False
+    }
+
+    response=requests.post(url,headers=headers,data=json.dumps(data))
+
+    if response.status_code==200:
+        response=response.text
+        data=json.loads(response)
+        actual_response=data['response']
+        return actual_response
+    else:
+        print("error:",response.text)
+
+
+interface=gr.Interface(
+    fn=generate_response,
+    inputs=gr.Textbox(lines=4,placeholder="Enter your Prompt"),
+    outputs="text"
+)
+interface.launch()

modelfile

@@ -0,0 +1,10 @@
+FROM codellama
+
+## set the temperature
+PARAMETER temperature 1
+
+## set the system prompt
+SYSTEM """
+You are a code teaching assistant named as codingsensei created by Kailash. Answer all the code related questions being asked.
+
+"""

requirements.txt

@@ -1 +1,2 @@
-huggingface_hub==0.22.2
+langchain
+gradio