Upload folder using huggingface_hub

.github/workflows/update_space.yml

@@ -0,0 +1,28 @@
+name: Run Python script
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v2
+
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.9'
+
+    - name: Install Gradio
+      run: python -m pip install gradio
+
+    - name: Log in to Hugging Face
+      run: python -c 'import huggingface_hub; huggingface_hub.login(token="${{ secrets.hf_token }}")'
+
+    - name: Deploy to Spaces
+      run: gradio deploy

.gitignore

@@ -0,0 +1,23 @@
+### AL ###
+#Template for AL projects for Dynamics 365 Business Central
+#launch.json folder
+.vscode/
+#Cache folder
+.alcache/
+#Symbols folder
+.alpackages/
+#Snapshots folder
+.snapshots/
+#Testing Output folder
+.output/
+#Extension App-file
+*.app
+#Rapid Application Development File
+rad.json
+#Translation Base-file
+*.g.xlf
+#License-file
+*.flf
+#Test results file
+TestResults.xml
+.venv

README.md

@@ -1,12 +1,6 @@
 ---
-title: Ollama Test
-emoji: 🏢
-colorFrom: green
-colorTo: gray
+title: Ollama_test
+app_file: app.py
 sdk: gradio
 sdk_version: 4.44.0
-app_file: app.py
-pinned: false
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,189 @@
+import gradio as gr
+import httpx
+import json
+import asyncio
+import os
+from chat_state import chat_state
+from config import OLLAMA_URL, DEFAULT_TEMPERATURE, DEFAULT_SYSTEM_MESSAGE
+
+theme = gr.themes.Soft(
+    primary_hue="yellow",
+    neutral_hue="neutral",
+    text_size="md",
+    spacing_size="md",
+    radius_size="md",
+    font=[gr.themes.GoogleFont('Montserrat'), gr.themes.GoogleFont('ui-sans-serif'), 'system-ui', 'sans-serif'],
+)
+
+
+async def fetch_available_models():
+    async with httpx.AsyncClient() as client:
+        try:
+            response = await client.get(f"{OLLAMA_URL}/api/tags")
+            response.raise_for_status()
+            data = response.json()
+            return [model["name"] for model in data.get("models", [])]
+        except httpx.HTTPStatusError as e:
+            print(f"Error fetching models: {e}")
+            return []
+
+async def get_model_info(model_name):
+    async with httpx.AsyncClient() as client:
+        try:
+            response = await client.post(f"{OLLAMA_URL}/api/show", json={"name": model_name})
+            response.raise_for_status()
+            return response.json()
+        except httpx.HTTPStatusError as e:
+            print(f"Error fetching model info: {e}")
+            return {}
+
+async def call_ollama_api(prompt, history):
+    messages = [{"role": "system", "content": chat_state.system_message}]
+    for user_msg, assistant_msg in history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if assistant_msg:
+            messages.append({"role": "assistant", "content": assistant_msg})
+    messages.append({"role": "user", "content": prompt})
+
+    payload = {
+        "model": chat_state.model,
+        "messages": messages,
+        "stream": True,
+        "temperature": chat_state.temperature
+    }
+    
+    async with httpx.AsyncClient() as client:
+        try:
+            async with client.stream("POST", f"{OLLAMA_URL}/api/chat", json=payload, timeout=30.0) as response:
+                response.raise_for_status()
+                full_response = ""
+                async for line in response.aiter_lines():
+                    if line:
+                        json_line = json.loads(line)
+                        message_content = json_line.get('message', {}).get('content', '')
+                        if message_content:
+                            full_response += message_content
+                            yield full_response
+                        if json_line.get('done'):
+                            break
+        except httpx.HTTPStatusError as e:
+            yield f"An error occurred: {e}"
+        except asyncio.TimeoutError:
+            yield "The request timed out. Please try again."
+
+async def user(user_message, history):
+    return "", history + [[user_message, None]]
+
+async def bot(history):
+    user_message = history[-1][0]
+    bot_message_generator = call_ollama_api(user_message, history[:-1])
+    async for message_content in bot_message_generator:
+        history[-1][1] = message_content
+        yield history
+
+def clear_chat():
+    return None
+
+def save_chat_history(history, filename="chat_history.json"):
+    with open(filename, "w") as f:
+        json.dump(history, f)
+    return f"Chat history saved to {filename}"
+
+def load_chat_history(filename="chat_history.json"):
+    try:
+        with open(filename, "r") as f:
+            return json.load(f)
+    except FileNotFoundError:
+        return None
+
+async def change_model(model_name):
+    chat_state.model = model_name
+    model_info = await get_model_info(model_name)
+    info_text = f"Model: {model_name}\n"
+    info_text += f"Parameter Size: {model_info.get('details', {}).get('parameter_size', 'Unknown')}\n"
+    info_text += f"Quantization: {model_info.get('details', {}).get('quantization_level', 'Unknown')}\n"
+    info_text += f"Format: {model_info.get('details', {}).get('format', 'Unknown')}"
+    return f"Model changed to {chat_state.model}", info_text
+
+def update_temperature(new_temp):
+    chat_state.temperature = float(new_temp)
+    return f"Temperature set to {chat_state.temperature}"
+
+def update_system_message(new_message):
+    chat_state.system_message = new_message
+    return f"System message updated: {chat_state.system_message}"
+
+async def initialize_interface():
+    chat_state.available_models = await fetch_available_models()
+    
+    with gr.Blocks(theme=theme) as demo:
+        gr.Markdown("# 🤖 Enhanced Ollama Chatbot Interface")
+        
+        with gr.Row():
+            with gr.Column(scale=7):
+                chatbot = gr.Chatbot(height=600, elem_id="chatbot")
+                with gr.Row():
+                    msg = gr.Textbox(
+                        label="Message",
+                        placeholder="Type your message here...",
+                        scale=4,
+                        elem_id="user-input"
+                    )
+                    send = gr.Button("Send", scale=1, elem_id="send-btn")
+            
+            with gr.Column(scale=3):
+                with gr.Accordion("Model Settings", open=True):
+                    model_dropdown = gr.Dropdown(
+                        choices=chat_state.available_models,
+                        label="Select Model",
+                        value=chat_state.available_models[0] if chat_state.available_models else None,
+                        elem_id="model-dropdown"
+                    )
+                    model_info = gr.Textbox(label="Model Information", interactive=False, lines=4)
+                    temp_slider = gr.Slider(
+                        minimum=0, maximum=1, value=DEFAULT_TEMPERATURE, step=0.1,
+                        label="Temperature",
+                        elem_id="temp-slider"
+                    )
+                
+                with gr.Accordion("System Message", open=False):
+                    system_message_input = gr.Textbox(
+                        label="System Message",
+                        value=DEFAULT_SYSTEM_MESSAGE,
+                        lines=3,
+                        elem_id="system-message"
+                    )
+                    update_system_button = gr.Button("Update System Message", elem_id="update-system-btn")
+                
+                with gr.Accordion("Chat Management", open=False):
+                    with gr.Row():
+                        clear = gr.Button("Clear Chat", elem_id="clear-btn")
+                        save_button = gr.Button("Save Chat", elem_id="save-btn")
+                        load_button = gr.Button("Load Chat", elem_id="load-btn")
+                
+                status_box = gr.Textbox(label="Status", interactive=False, elem_id="status-box")
+        
+        # Event handlers
+        send_event = msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(
+            bot, chatbot, chatbot
+        )
+        send.click(user, [msg, chatbot], [msg, chatbot], queue=False).then(
+            bot, chatbot, chatbot
+        )
+        clear.click(clear_chat, outputs=[chatbot])
+        model_dropdown.change(change_model, inputs=[model_dropdown], outputs=[status_box, model_info])
+        temp_slider.change(update_temperature, inputs=[temp_slider], outputs=[status_box])
+        update_system_button.click(update_system_message, inputs=[system_message_input], outputs=[status_box])
+        save_button.click(save_chat_history, inputs=[chatbot], outputs=[status_box])
+        load_button.click(load_chat_history, outputs=[chatbot])
+
+        # Initialize the first model
+        if chat_state.available_models:
+            chat_state.model = chat_state.available_models[0]
+
+    return demo
+
+if __name__ == "__main__":
+    demo = asyncio.run(initialize_interface())
+    demo.launch(share=True)

chat_history.json

@@ -0,0 +1 @@
+[["F", "I'm sorry, but I cannot assist you with that. Could you please provide more context or clarify your question?"]]

chat_state.py

@@ -0,0 +1,10 @@
+from config import DEFAULT_TEMPERATURE, DEFAULT_SYSTEM_MESSAGE
+
+class ChatState:
+    def __init__(self):
+        self.model = None
+        self.temperature = DEFAULT_TEMPERATURE
+        self.system_message = DEFAULT_SYSTEM_MESSAGE
+        self.available_models = []
+
+chat_state = ChatState()

config.py

@@ -0,0 +1,4 @@
+# Configuration and constants
+OLLAMA_URL = "http://localhost:11434"
+DEFAULT_TEMPERATURE = 0.7
+DEFAULT_SYSTEM_MESSAGE = "You are a helpful AI assistant."

constraints.txt

@@ -0,0 +1,84 @@
+# requirements.txt
+
+aiofiles==23.2.1
+annotated-types==0.7.0
+anyio==4.6.0
+asyncio==3.4.3
+certifi==2024.8.30
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+contourpy==1.3.0
+cycler==0.12.1
+fastapi==0.115.0
+ffmpy==0.4.0
+filelock==3.16.1
+fonttools==4.53.1
+fsspec==2024.9.0
+gradio==4.44.0
+gradio_client==1.3.0
+grpcio==1.66.1
+grpcio-tools==1.66.1
+h11==0.14.0
+h2==4.1.0
+hpack==4.0.0
+httpcore==1.0.5
+httpx==0.27.2
+huggingface-hub==0.25.0
+hyperframe==6.0.1
+idna==3.10
+importlib_resources==6.4.5
+Jinja2==3.1.4
+joblib==1.4.2
+kiwisolver==1.4.7
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.2
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.3
+numpy==2.1.1
+orjson==3.10.7
+packaging==24.1
+pandas==2.2.3
+pillow==10.4.0
+portalocker==2.10.1
+protobuf==5.28.2
+pydantic==2.9.2
+pydantic_core==2.23.4
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-multipart==0.0.10
+pytz==2024.2
+pywin32==306
+PyYAML==6.0.2
+qdrant-client==1.11.2
+regex==2024.9.11
+requests==2.32.3
+rich==13.8.1
+ruff==0.6.7
+safetensors==0.4.5
+scikit-learn==1.5.2
+scipy==1.14.1
+semantic-version==2.10.0
+sentence-transformers==3.1.1
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.6
+sympy==1.13.3
+threadpoolctl==3.5.0
+tiktoken==0.7.0
+tokenizers==0.19.1
+tomlkit==0.12.0
+torch==2.4.1
+tqdm==4.66.5
+transformers==4.44.2
+typer==0.12.5
+typing_extensions==4.12.2
+tzdata==2024.1
+urllib3==2.2.3
+uvicorn==0.30.6
+websockets==12.0

requirements.txt

@@ -0,0 +1,5 @@
+gradio==gradio>=3.23.0
+httpx==httpx>=0.24.0
+asyncio
+json
+os