coding

.gitattributes

@@ -1 +1,35 @@
-Animated_Logo_Video_Ready.gif filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -1,3 +1,5 @@
+.gradio/
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
@@ -19,18 +21,16 @@ lib64/
 parts/
 sdist/
 var/
+wheels/
+share/python-wheels/
 *.egg-info/
 .installed.cfg
 *.egg
 MANIFEST
 
-# Virtual environments
-venv/
-env/
-ENV/
-.venv/
-
 # PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
 *.manifest
 *.spec
 
@@ -48,34 +48,115 @@ htmlcov/
 nosetests.xml
 coverage.xml
 *.cover
+*.py,cover
 .hypothesis/
 .pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
 
 # Jupyter Notebook
 .ipynb_checkpoints
 
+# IPython
+profile_default/
+ipython_config.py
+
 # pyenv
-.python-version
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
 
 # mypy
 .mypy_cache/
 .dmypy.json
+dmypy.json
 
 # Pyre type checker
 .pyre/
 
-# Gradio cache
-log/
-logs/
-
-# System files
-.DS_Store
-Thumbs.db
+# pytype static type analyzer
+.pytype/
 
-# Lock files
-uv.lock
-poetry.lock
-Pipfile.lock
+# Cython debug symbols
+cython_debug/
 
-# VSCode
-.vscode/ 
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

.pre-commit-config.yaml

@@ -0,0 +1,32 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: check-executables-have-shebangs
+      - id: check-json
+      - id: check-merge-conflict
+      - id: check-shebang-scripts-are-executable
+      - id: check-toml
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+        args: ["--fix=lf"]
+      - id: requirements-txt-fixer
+      - id: trailing-whitespace
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.8.6
+    hooks:
+      - id: ruff
+        args: ["--fix"]
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.14.1
+    hooks:
+      - id: mypy
+        args: ["--ignore-missing-imports"]
+        additional_dependencies:
+          [
+            "types-python-slugify",
+            "types-requests",
+            "types-PyYAML",
+            "types-pytz",
+          ]

.python-version

@@ -0,0 +1 @@
+3.10

.vscode/extensions.json

@@ -0,0 +1,8 @@
+{
+    "recommendations": [
+        "ms-python.python",
+        "charliermarsh.ruff",
+        "streetsidesoftware.code-spell-checker",
+        "tamasfe.even-better-toml"
+    ]
+}

.vscode/settings.json

@@ -0,0 +1,16 @@
+{
+    "editor.formatOnSave": true,
+    "files.insertFinalNewline": false,
+    "[python]": {
+        "editor.defaultFormatter": "charliermarsh.ruff",
+        "editor.formatOnType": true,
+        "editor.codeActionsOnSave": {
+            "source.fixAll.ruff": "explicit"
+        }
+    },
+    "[jupyter]": {
+        "files.insertFinalNewline": false
+    },
+    "notebook.output.scrolling": true,
+    "notebook.formatOnSave.enabled": true
+}

README.md

@@ -1,130 +1,13 @@
 ---
-title: Anycoder
+title: Anychat
 emoji: 🏢
 colorFrom: indigo
 colorTo: indigo
 sdk: gradio
-sdk_version: 5.38.1
+sdk_version: 5.12.0
 app_file: app.py
 pinned: false
 disable_embedding: true
-hf_oauth: true
-hf_oauth_scopes:
-- manage-repos
 ---
 
-# AnyCoder - AI Code Generator
-
-AnyCoder is an AI-powered code generator that helps you create applications by describing them in plain English. It supports multiple AI models, multimodal input, website redesign, and one-click deployment to Hugging Face Spaces. The UI is built with pure Gradio theming for a minimal, modern experience.
-
-## Features
-
-- **Multi-Model Support**: Choose from Moonshot Kimi-K2, DeepSeek V3, DeepSeek R1, ERNIE-4.5-VL, MiniMax M1, Qwen3-235B-A22B, SmolLM3-3B, and GLM-4.1V-9B-Thinking
-- **Flexible Input**: Describe your app in text, upload a UI design image (for multimodal models), provide a reference file (PDF, TXT, MD, CSV, DOCX, or image), or enter a website URL for redesign
-- **Web Search Integration**: Enable real-time web search (Tavily, with advanced search depth) to enhance code generation with up-to-date information and best practices
-- **Code Generation**: Generate code in HTML, Python, JS, and more. Special support for transformers.js apps (outputs index.html, index.js, style.css)
-- **Live Preview**: Instantly preview generated HTML in a sandboxed iframe
-- **Modify Existing Code**: Use search/replace block format to update generated HTML
-- **One-Click Deployment**: Deploy your app to Hugging Face Spaces (Gradio, Streamlit, Static HTML, or Transformers.js) with OAuth login
-- **History & Examples**: Chat-like history of all interactions and quick example prompts for fast prototyping
-- **Minimal, Modern UI**: Built with Gradio 5.x, using only built-in theming and styling (no custom CSS)
-
-## Installation
-
-1. Clone the repository:
-```bash
-git clone <repository-url>
-cd anycoder
-```
-2. Install dependencies:
-```bash
-pip install -r requirements.txt
-```
-3. Set up environment variables:
-```bash
-export HF_TOKEN="your_huggingface_token"
-export TAVILY_API_KEY="your_tavily_api_key"  # Optional, for web search feature
-```
-
-## Usage
-
-1. Run the application:
-```bash
-python app.py
-```
-2. Open your browser and navigate to the provided URL
-3. Describe your application in the text input field, or:
-   - Upload a UI design image (for ERNIE-4.5-VL or GLM-4.1V-9B-Thinking)
-   - Upload a reference file (PDF, TXT, MD, CSV, DOCX, or image)
-   - Enter a website URL for redesign (the app will extract and analyze the HTML and content)
-   - Enable web search for up-to-date information
-   - Choose a different AI model or code language
-4. Click "Generate" to create your code
-5. View the generated code in the Code tab or see it in action in the Preview tab
-6. Use the History tab to review previous generations
-7. **Deploy to Space**: Enter a title, select SDK, and click "🚀 Deploy App" to publish your application (OAuth login required)
-
-## Supported Models
-
-- Moonshot Kimi-K2
-- DeepSeek V3
-- DeepSeek R1
-- ERNIE-4.5-VL (multimodal)
-- MiniMax M1
-- Qwen3-235B-A22B
-- SmolLM3-3B
-- GLM-4.1V-9B-Thinking (multimodal)
-
-## Input Options
-
-- **Text Prompt**: Describe your app or code requirements
-- **Image Upload**: For multimodal models, upload a UI design image to generate code from visuals
-- **File Upload**: Provide a reference file (PDF, TXT, MD, CSV, DOCX, or image) for code generation or text extraction (OCR for images)
-- **Website URL**: Enter a URL to extract and redesign the website (HTML and content are analyzed and modernized)
-
-## Web Search Feature
-
-- Enable the "Web search" toggle to use Tavily for real-time information (requires TAVILY_API_KEY)
-- Uses advanced search depth for best results
-
-## Code Generation & Modification
-
-- Generates code in HTML, Python, JS, and more (selectable via dropdown)
-- Special support for transformers.js apps (outputs index.html, index.js, style.css)
-- Svelte apps
-- For HTML, provides a live preview in a sandboxed iframe
-- For modification requests, uses a search/replace block format to update existing HTML
-
-## Deployment
-
-- Deploy generated apps to Hugging Face Spaces directly from the UI
-- Supported SDKs: Gradio (Python), Streamlit (Python), Static (HTML), Transformers.js
-- OAuth login with Hugging Face is required for deployment to user-owned Spaces
-
-## History & Examples
-
-- Maintains a chat-like history of user/assistant interactions
-- Quick example prompts are available in the sidebar for fast prototyping
-
-## UI/UX
-
-- Built with Gradio 5.x, using only Gradio's built-in theming and styling (no custom CSS)
-- Minimal, uncluttered sidebar and interface
-
-## Environment Variables
-
-- `HF_TOKEN`: Your Hugging Face API token (required)
-- `TAVILY_API_KEY`: Your Tavily API key (optional, for web search)
-
-## Project Structure
-
-```
-anycoder/
-├── app.py          # Main application (all logic and UI)
-├── requirements.txt
-├── README.md       # This file
-```
-
-## License
-
-[Add your license information here]
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app_allenai.py

@@ -0,0 +1,67 @@
+import gradio as gr
+from gradio_client import Client
+
+MODELS = {"OLMo-2-1124-13B-Instruct": "akhaliq/olmo-anychat", "Llama-3.1-Tulu-3-8B": "akhaliq/allen-test"}
+
+
+def create_chat_fn(client):
+    def chat(message, history):
+        response = client.predict(
+            message=message,
+            system_prompt="You are a helpful AI assistant.",
+            temperature=0.7,
+            max_new_tokens=1024,
+            top_k=40,
+            repetition_penalty=1.1,
+            top_p=0.95,
+            api_name="/chat",
+        )
+        return response
+
+    return chat
+
+
+def set_client_for_session(model_name, request: gr.Request):
+    headers = {}
+    if request and hasattr(request, "request") and hasattr(request.request, "headers"):
+        x_ip_token = request.request.headers.get("x-ip-token")
+        if x_ip_token:
+            headers["X-IP-Token"] = x_ip_token
+
+    return Client(MODELS[model_name], headers=headers)
+
+
+def safe_chat_fn(message, history, client):
+    if client is None:
+        return "Error: Client not initialized. Please refresh the page."
+    return create_chat_fn(client)(message, history)
+
+
+with gr.Blocks() as demo:
+    client = gr.State()
+
+    model_dropdown = gr.Dropdown(
+        choices=list(MODELS.keys()), value="OLMo-2-1124-13B-Instruct", label="Select Model", interactive=True
+    )
+
+    chat_interface = gr.ChatInterface(fn=safe_chat_fn, additional_inputs=[client])
+
+    # Update client when model changes
+    def update_model(model_name, request):
+        return set_client_for_session(model_name, request)
+
+    model_dropdown.change(
+        fn=update_model,
+        inputs=[model_dropdown],
+        outputs=[client],
+    )
+
+    # Initialize client on page load
+    demo.load(
+        fn=set_client_for_session,
+        inputs=gr.State("OLMo-2-1124-13B-Instruct"),
+        outputs=client,
+    )
+
+if __name__ == "__main__":
+    demo.launch()

app_cerebras.py

@@ -0,0 +1,19 @@
+import os
+
+import cerebras_gradio
+
+from utils import get_app
+
+demo = get_app(
+    models=[
+        "llama3.1-8b",
+        "llama3.1-70b",
+        "llama3.1-405b",
+    ],
+    default_model="llama3.1-70b",
+    src=cerebras_gradio.registry,
+    accept_token=not os.getenv("CEREBRAS_API_KEY"),
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_claude.py

@@ -0,0 +1,21 @@
+import os
+
+import anthropic_gradio
+
+from utils import get_app
+
+demo = get_app(
+    models=[
+        "claude-3-5-sonnet-20241022",
+        "claude-3-5-haiku-20241022",
+        "claude-3-opus-20240229",
+        "claude-3-sonnet-20240229",
+        "claude-3-haiku-20240307",
+    ],
+    default_model="claude-3-5-sonnet-20241022",
+    src=anthropic_gradio.registry,
+    accept_token=not os.getenv("ANTHROPIC_API_KEY"),
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_cohere.py

@@ -0,0 +1,21 @@
+import os
+
+import cohere_gradio
+
+from utils import get_app
+
+demo = get_app(
+    models=[
+        "command-r",
+        "command-r-08-2024",
+        "command-r-plus",
+        "command-r-plus-08-2024",
+        "command-r7b-12-2024",
+    ],
+    default_model="command-r7b-12-2024",
+    src=cohere_gradio.registry,
+    accept_token=not os.getenv("COHERE_API_KEY"),
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_compare.py

@@ -0,0 +1,210 @@
+import os
+
+import google.generativeai as genai
+import gradio as gr
+import openai
+from anthropic import Anthropic
+from openai import OpenAI  # Add explicit OpenAI import
+
+
+def get_all_models():
+    """Get all available models from the registries."""
+    return [
+        "SambaNova: Meta-Llama-3.2-1B-Instruct",
+        "SambaNova: Meta-Llama-3.2-3B-Instruct",
+        "SambaNova: Llama-3.2-11B-Vision-Instruct",
+        "SambaNova: Llama-3.2-90B-Vision-Instruct",
+        "SambaNova: Meta-Llama-3.1-8B-Instruct",
+        "SambaNova: Meta-Llama-3.1-70B-Instruct",
+        "SambaNova: Meta-Llama-3.1-405B-Instruct",
+        "Hyperbolic: Qwen/Qwen2.5-Coder-32B-Instruct",
+        "Hyperbolic: meta-llama/Llama-3.2-3B-Instruct",
+        "Hyperbolic: meta-llama/Meta-Llama-3.1-8B-Instruct",
+        "Hyperbolic: meta-llama/Meta-Llama-3.1-70B-Instruct",
+        "Hyperbolic: meta-llama/Meta-Llama-3-70B-Instruct",
+        "Hyperbolic: NousResearch/Hermes-3-Llama-3.1-70B",
+        "Hyperbolic: Qwen/Qwen2.5-72B-Instruct",
+        "Hyperbolic: deepseek-ai/DeepSeek-V2.5",
+        "Hyperbolic: meta-llama/Meta-Llama-3.1-405B-Instruct",
+    ]
+
+
+def generate_discussion_prompt(original_question: str, previous_responses: list[str]) -> str:
+    """Generate a prompt for models to discuss and build upon previous
+    responses.
+    """
+    prompt = f"""You are participating in a multi-AI discussion about this question: "{original_question}"
+
+Previous responses from other AI models:
+{chr(10).join(f"- {response}" for response in previous_responses)}
+
+Please provide your perspective while:
+1. Acknowledging key insights from previous responses
+2. Adding any missing important points
+3. Respectfully noting if you disagree with anything and explaining why
+4. Building towards a complete answer
+
+Keep your response focused and concise (max 3-4 paragraphs)."""
+    return prompt
+
+
+def generate_consensus_prompt(original_question: str, discussion_history: list[str]) -> str:
+    """Generate a prompt for final consensus building."""
+    return f"""Review this multi-AI discussion about: "{original_question}"
+
+Discussion history:
+{chr(10).join(discussion_history)}
+
+As a final synthesizer, please:
+1. Identify the key points where all models agreed
+2. Explain how any disagreements were resolved
+3. Present a clear, unified answer that represents our collective best understanding
+4. Note any remaining uncertainties or caveats
+
+Keep the final consensus concise but complete."""
+
+
+def chat_with_openai(model: str, messages: list[dict], api_key: str | None) -> str:
+    import openai
+
+    client = openai.OpenAI(api_key=api_key)
+    response = client.chat.completions.create(model=model, messages=messages)
+    return response.choices[0].message.content
+
+
+def chat_with_anthropic(messages: list[dict], api_key: str | None) -> str:
+    """Chat with Anthropic's Claude model."""
+    client = Anthropic(api_key=api_key)
+    response = client.messages.create(model="claude-3-sonnet-20240229", messages=messages, max_tokens=1024)
+    return response.content[0].text
+
+
+def chat_with_gemini(messages: list[dict], api_key: str | None) -> str:
+    """Chat with Gemini Pro model."""
+    genai.configure(api_key=api_key)
+    model = genai.GenerativeModel("gemini-pro")
+
+    # Convert messages to Gemini format
+    gemini_messages = []
+    for msg in messages:
+        role = "user" if msg["role"] == "user" else "model"
+        gemini_messages.append({"role": role, "parts": [msg["content"]]})
+
+    response = model.generate_content([m["parts"][0] for m in gemini_messages])
+    return response.text
+
+
+def chat_with_sambanova(
+    messages: list[dict], api_key: str | None, model_name: str = "Llama-3.2-90B-Vision-Instruct"
+) -> str:
+    """Chat with SambaNova's models using their OpenAI-compatible API."""
+    client = openai.OpenAI(
+        api_key=api_key,
+        base_url="https://api.sambanova.ai/v1",
+    )
+
+    response = client.chat.completions.create(
+        model=model_name,
+        messages=messages,
+        temperature=0.1,
+        top_p=0.1,  # Use the specific model name passed in
+    )
+    return response.choices[0].message.content
+
+
+def chat_with_hyperbolic(
+    messages: list[dict], api_key: str | None, model_name: str = "Qwen/Qwen2.5-Coder-32B-Instruct"
+) -> str:
+    """Chat with Hyperbolic's models using their OpenAI-compatible API."""
+    client = OpenAI(api_key=api_key, base_url="https://api.hyperbolic.xyz/v1")
+
+    # Add system message to the start of the messages list
+    full_messages = [
+        {"role": "system", "content": "You are a helpful assistant. Be descriptive and clear."},
+        *messages,
+    ]
+
+    response = client.chat.completions.create(
+        model=model_name,  # Use the specific model name passed in
+        messages=full_messages,
+        temperature=0.7,
+        max_tokens=1024,
+    )
+    return response.choices[0].message.content
+
+
+def multi_model_consensus(
+    question: str, selected_models: list[str], rounds: int = 3, progress: gr.Progress = gr.Progress()
+) -> list[tuple[str, str]]:
+    if not selected_models:
+        raise gr.Error("Please select at least one model to chat with.")
+
+    chat_history = []
+    progress(0, desc="Getting responses from all models...")
+
+    # Get responses from all models in parallel
+    for i, model in enumerate(selected_models):
+        provider, model_name = model.split(": ", 1)
+        progress((i + 1) / len(selected_models), desc=f"Getting response from {model}...")
+
+        try:
+            if provider == "Anthropic":
+                api_key = os.getenv("ANTHROPIC_API_KEY")
+                response = chat_with_anthropic(messages=[{"role": "user", "content": question}], api_key=api_key)
+            elif provider == "SambaNova":
+                api_key = os.getenv("SAMBANOVA_API_KEY")
+                response = chat_with_sambanova(
+                    messages=[
+                        {"role": "system", "content": "You are a helpful assistant"},
+                        {"role": "user", "content": question},
+                    ],
+                    api_key=api_key,
+                    model_name=model_name,
+                )
+            elif provider == "Hyperbolic":
+                api_key = os.getenv("HYPERBOLIC_API_KEY")
+                response = chat_with_hyperbolic(
+                    messages=[{"role": "user", "content": question}],
+                    api_key=api_key,
+                    model_name=model_name,
+                )
+            else:  # Gemini
+                api_key = os.getenv("GEMINI_API_KEY")
+                response = chat_with_gemini(messages=[{"role": "user", "content": question}], api_key=api_key)
+
+            chat_history.append((model, response))
+        except Exception as e:
+            chat_history.append((model, f"Error: {e!s}"))
+
+    progress(1.0, desc="Done!")
+    return chat_history
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Model Response Comparison")
+    gr.Markdown("""Select multiple models to compare their responses""")
+
+    with gr.Row():
+        with gr.Column():
+            model_selector = gr.Dropdown(
+                choices=get_all_models(),
+                multiselect=True,
+                label="Select Models",
+                info="Choose models to compare",
+                value=["SambaNova: Llama-3.2-90B-Vision-Instruct", "Hyperbolic: Qwen/Qwen2.5-Coder-32B-Instruct"],
+            )
+
+    chatbot = gr.Chatbot(height=600, label="Model Responses")
+    msg = gr.Textbox(label="Prompt", placeholder="Ask a question to compare model responses...")
+
+    def respond(message, selected_models):
+        chat_history = multi_model_consensus(message, selected_models, rounds=1)
+        return chat_history
+
+    msg.submit(respond, [msg, model_selector], [chatbot])
+
+for fn in demo.fns.values():
+    fn.api_name = False
+
+if __name__ == "__main__":
+    demo.launch()

app_crew.py

@@ -0,0 +1,8 @@
+import ai_gradio
+import gradio as gr
+
+demo = gr.load(
+    name="crewai:gpt-4-turbo",
+    crew_type="article",  # or 'support'
+    src=ai_gradio.registry,
+)

app_deepseek.py

@@ -0,0 +1,23 @@
+import ai_gradio
+
+from utils_ai_gradio import get_app
+
+# Get the hyperbolic models but keep their full names for loading
+DEEPSEEK_MODELS_FULL = [k for k in ai_gradio.registry.keys() if k.startswith("deepseek:")]
+
+# Create display names without the prefix
+DEEPSEEK_MODELS_DISPLAY = [k.replace("deepseek:", "") for k in DEEPSEEK_MODELS_FULL]
+
+
+# Create and launch the interface using get_app utility
+demo = get_app(
+    models=DEEPSEEK_MODELS_FULL,  # Use the full names with prefix
+    default_model=DEEPSEEK_MODELS_FULL[-1],
+    dropdown_label="Select DeepSeek Model",
+    choices=DEEPSEEK_MODELS_DISPLAY,  # Display names without prefix
+    fill_height=True,
+    coder=True,
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_experimental.py

@@ -0,0 +1,300 @@
+import os
+import random
+
+import google.generativeai as genai
+import gradio as gr
+import openai
+from anthropic import Anthropic
+from openai import OpenAI  # Add explicit OpenAI import
+
+
+def get_all_models():
+    """Get all available models from the registries."""
+    return [
+        "SambaNova: Meta-Llama-3.2-1B-Instruct",
+        "SambaNova: Meta-Llama-3.2-3B-Instruct",
+        "SambaNova: Llama-3.2-11B-Vision-Instruct",
+        "SambaNova: Llama-3.2-90B-Vision-Instruct",
+        "SambaNova: Meta-Llama-3.1-8B-Instruct",
+        "SambaNova: Meta-Llama-3.1-70B-Instruct",
+        "SambaNova: Meta-Llama-3.1-405B-Instruct",
+        "Hyperbolic: Qwen/Qwen2.5-Coder-32B-Instruct",
+        "Hyperbolic: meta-llama/Llama-3.2-3B-Instruct",
+        "Hyperbolic: meta-llama/Meta-Llama-3.1-8B-Instruct",
+        "Hyperbolic: meta-llama/Meta-Llama-3.1-70B-Instruct",
+        "Hyperbolic: meta-llama/Meta-Llama-3-70B-Instruct",
+        "Hyperbolic: NousResearch/Hermes-3-Llama-3.1-70B",
+        "Hyperbolic: Qwen/Qwen2.5-72B-Instruct",
+        "Hyperbolic: deepseek-ai/DeepSeek-V2.5",
+        "Hyperbolic: meta-llama/Meta-Llama-3.1-405B-Instruct",
+    ]
+
+
+def generate_discussion_prompt(original_question: str, previous_responses: list[str]) -> str:
+    """Generate a prompt for models to discuss and build upon previous
+    responses.
+    """
+    prompt = f"""You are participating in a multi-AI discussion about this question: "{original_question}"
+
+Previous responses from other AI models:
+{chr(10).join(f"- {response}" for response in previous_responses)}
+
+Please provide your perspective while:
+1. Acknowledging key insights from previous responses
+2. Adding any missing important points
+3. Respectfully noting if you disagree with anything and explaining why
+4. Building towards a complete answer
+
+Keep your response focused and concise (max 3-4 paragraphs)."""
+    return prompt
+
+
+def generate_consensus_prompt(original_question: str, discussion_history: list[str]) -> str:
+    """Generate a prompt for final consensus building."""
+    return f"""Review this multi-AI discussion about: "{original_question}"
+
+Discussion history:
+{chr(10).join(discussion_history)}
+
+As a final synthesizer, please:
+1. Identify the key points where all models agreed
+2. Explain how any disagreements were resolved
+3. Present a clear, unified answer that represents our collective best understanding
+4. Note any remaining uncertainties or caveats
+
+Keep the final consensus concise but complete."""
+
+
+def chat_with_openai(model: str, messages: list[dict], api_key: str | None) -> str:
+    import openai
+
+    client = openai.OpenAI(api_key=api_key)
+    response = client.chat.completions.create(model=model, messages=messages)
+    return response.choices[0].message.content
+
+
+def chat_with_anthropic(messages: list[dict], api_key: str | None) -> str:
+    """Chat with Anthropic's Claude model."""
+    client = Anthropic(api_key=api_key)
+    response = client.messages.create(model="claude-3-sonnet-20240229", messages=messages, max_tokens=1024)
+    return response.content[0].text
+
+
+def chat_with_gemini(messages: list[dict], api_key: str | None) -> str:
+    """Chat with Gemini Pro model."""
+    genai.configure(api_key=api_key)
+    model = genai.GenerativeModel("gemini-pro")
+
+    # Convert messages to Gemini format
+    gemini_messages = []
+    for msg in messages:
+        role = "user" if msg["role"] == "user" else "model"
+        gemini_messages.append({"role": role, "parts": [msg["content"]]})
+
+    response = model.generate_content([m["parts"][0] for m in gemini_messages])
+    return response.text
+
+
+def chat_with_sambanova(
+    messages: list[dict], api_key: str | None, model_name: str = "Llama-3.2-90B-Vision-Instruct"
+) -> str:
+    """Chat with SambaNova's models using their OpenAI-compatible API."""
+    client = openai.OpenAI(
+        api_key=api_key,
+        base_url="https://api.sambanova.ai/v1",
+    )
+
+    response = client.chat.completions.create(
+        model=model_name,
+        messages=messages,
+        temperature=0.1,
+        top_p=0.1,  # Use the specific model name passed in
+    )
+    return response.choices[0].message.content
+
+
+def chat_with_hyperbolic(
+    messages: list[dict], api_key: str | None, model_name: str = "Qwen/Qwen2.5-Coder-32B-Instruct"
+) -> str:
+    """Chat with Hyperbolic's models using their OpenAI-compatible API."""
+    client = OpenAI(api_key=api_key, base_url="https://api.hyperbolic.xyz/v1")
+
+    # Add system message to the start of the messages list
+    full_messages = [
+        {"role": "system", "content": "You are a helpful assistant. Be descriptive and clear."},
+        *messages,
+    ]
+
+    response = client.chat.completions.create(
+        model=model_name,  # Use the specific model name passed in
+        messages=full_messages,
+        temperature=0.7,
+        max_tokens=1024,
+    )
+    return response.choices[0].message.content
+
+
+def multi_model_consensus(
+    question: str, selected_models: list[str], rounds: int = 3, progress: gr.Progress = gr.Progress()
+) -> list[tuple[str, str]]:
+    if not selected_models:
+        raise gr.Error("Please select at least one model to chat with.")
+
+    chat_history = []
+    discussion_history = []
+
+    # Initial responses
+    progress(0, desc="Getting initial responses...")
+    initial_responses = []
+    for i, model in enumerate(selected_models):
+        provider, model_name = model.split(": ", 1)
+
+        try:
+            if provider == "Anthropic":
+                api_key = os.getenv("ANTHROPIC_API_KEY")
+                response = chat_with_anthropic(messages=[{"role": "user", "content": question}], api_key=api_key)
+            elif provider == "SambaNova":
+                api_key = os.getenv("SAMBANOVA_API_KEY")
+                response = chat_with_sambanova(
+                    messages=[
+                        {"role": "system", "content": "You are a helpful assistant"},
+                        {"role": "user", "content": question},
+                    ],
+                    api_key=api_key,
+                )
+            elif provider == "Hyperbolic":  # Add Hyperbolic case
+                api_key = os.getenv("HYPERBOLIC_API_KEY")
+                response = chat_with_hyperbolic(messages=[{"role": "user", "content": question}], api_key=api_key)
+            else:  # Gemini
+                api_key = os.getenv("GEMINI_API_KEY")
+                response = chat_with_gemini(messages=[{"role": "user", "content": question}], api_key=api_key)
+
+            initial_responses.append(f"{model}: {response}")
+            discussion_history.append(f"Initial response from {model}:\n{response}")
+            chat_history.append((f"Initial response from {model}", response))
+        except Exception as e:
+            chat_history.append((f"Error from {model}", str(e)))
+
+    # Discussion rounds
+    for round_num in range(rounds):
+        progress((round_num + 1) / (rounds + 2), desc=f"Discussion round {round_num + 1}...")
+        round_responses = []
+
+        random.shuffle(selected_models)  # Randomize order each round
+        for model in selected_models:
+            provider, model_name = model.split(": ", 1)
+
+            try:
+                discussion_prompt = generate_discussion_prompt(question, discussion_history)
+                if provider == "Anthropic":
+                    api_key = os.getenv("ANTHROPIC_API_KEY")
+                    response = chat_with_anthropic(
+                        messages=[{"role": "user", "content": discussion_prompt}], api_key=api_key
+                    )
+                elif provider == "SambaNova":
+                    api_key = os.getenv("SAMBANOVA_API_KEY")
+                    response = chat_with_sambanova(
+                        messages=[
+                            {"role": "system", "content": "You are a helpful assistant"},
+                            {"role": "user", "content": discussion_prompt},
+                        ],
+                        api_key=api_key,
+                    )
+                elif provider == "Hyperbolic":  # Add Hyperbolic case
+                    api_key = os.getenv("HYPERBOLIC_API_KEY")
+                    response = chat_with_hyperbolic(
+                        messages=[{"role": "user", "content": discussion_prompt}], api_key=api_key
+                    )
+                else:  # Gemini
+                    api_key = os.getenv("GEMINI_API_KEY")
+                    response = chat_with_gemini(
+                        messages=[{"role": "user", "content": discussion_prompt}], api_key=api_key
+                    )
+
+                round_responses.append(f"{model}: {response}")
+                discussion_history.append(f"Round {round_num + 1} - {model}:\n{response}")
+                chat_history.append((f"Round {round_num + 1} - {model}", response))
+            except Exception as e:
+                chat_history.append((f"Error from {model} in round {round_num + 1}", str(e)))
+
+    # Final consensus
+    progress(0.9, desc="Building final consensus...")
+    model = selected_models[0]
+    provider, model_name = model.split(": ", 1)
+
+    try:
+        consensus_prompt = generate_consensus_prompt(question, discussion_history)
+        if provider == "Anthropic":
+            api_key = os.getenv("ANTHROPIC_API_KEY")
+            final_consensus = chat_with_anthropic(
+                messages=[{"role": "user", "content": consensus_prompt}], api_key=api_key
+            )
+        elif provider == "SambaNova":
+            api_key = os.getenv("SAMBANOVA_API_KEY")
+            final_consensus = chat_with_sambanova(
+                messages=[
+                    {"role": "system", "content": "You are a helpful assistant"},
+                    {"role": "user", "content": consensus_prompt},
+                ],
+                api_key=api_key,
+            )
+        elif provider == "Hyperbolic":  # Add Hyperbolic case
+            api_key = os.getenv("HYPERBOLIC_API_KEY")
+            final_consensus = chat_with_hyperbolic(
+                messages=[{"role": "user", "content": consensus_prompt}], api_key=api_key
+            )
+        else:  # Gemini
+            api_key = os.getenv("GEMINI_API_KEY")
+            final_consensus = chat_with_gemini(
+                messages=[{"role": "user", "content": consensus_prompt}], api_key=api_key
+            )
+    except Exception as e:
+        final_consensus = f"Error getting consensus from {model}: {e!s}"
+
+    chat_history.append(("Final Consensus", final_consensus))
+
+    progress(1.0, desc="Done!")
+    return chat_history
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Experimental Multi-Model Consensus Chat")
+    gr.Markdown(
+        """Select multiple models to collaborate on answering your question.
+                The models will discuss with each other and attempt to reach a consensus.
+                Maximum 3 models can be selected at once."""
+    )
+
+    with gr.Row():
+        with gr.Column():
+            model_selector = gr.Dropdown(
+                choices=get_all_models(),
+                multiselect=True,
+                label="Select Models (max 3)",
+                info="Choose up to 3 models to participate in the discussion",
+                value=["SambaNova: Llama-3.2-90B-Vision-Instruct", "Hyperbolic: Qwen/Qwen2.5-Coder-32B-Instruct"],
+                max_choices=3,
+            )
+            rounds_slider = gr.Slider(
+                minimum=1,
+                maximum=2,
+                value=1,
+                step=1,
+                label="Discussion Rounds",
+                info="Number of rounds of discussion between models",
+            )
+
+    chatbot = gr.Chatbot(height=600, label="Multi-Model Discussion")
+    msg = gr.Textbox(label="Your Question", placeholder="Ask a question for the models to discuss...")
+
+    def respond(message, selected_models, rounds):
+        chat_history = multi_model_consensus(message, selected_models, rounds)
+        return chat_history
+
+    msg.submit(respond, [msg, model_selector, rounds_slider], [chatbot], api_name="consensus_chat")
+
+for fn in demo.fns.values():
+    fn.api_name = False
+
+if __name__ == "__main__":
+    demo.launch()

app_fal.py

@@ -0,0 +1,16 @@
+import fal_gradio
+
+from utils import get_app
+
+demo = get_app(
+    models=[
+        "fal-ai/ltx-video",
+        "fal-ai/ltx-video/image-to-video",
+        "fal-ai/luma-photon",
+    ],
+    default_model="fal-ai/luma-photon",
+    src=fal_gradio.registry,
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_fireworks.py

@@ -0,0 +1,19 @@
+import os
+
+import fireworks_gradio
+
+from utils import get_app
+
+demo = get_app(
+    models=[
+        "f1-preview",
+        "f1-mini-preview",
+        "llama-v3p3-70b-instruct",
+    ],
+    default_model="llama-v3p3-70b-instruct",
+    src=fireworks_gradio.registry,
+    accept_token=not os.getenv("FIREWORKS_API_KEY"),
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_gemini.py

@@ -0,0 +1,22 @@
+import ai_gradio
+
+from utils_ai_gradio import get_app
+
+# Get the Gemini models but keep their full names for loading
+GEMINI_MODELS_FULL = [k for k in ai_gradio.registry if k.startswith("gemini:")]
+
+# Create display names without the prefix
+GEMINI_MODELS_DISPLAY = [k.replace("gemini:", "") for k in GEMINI_MODELS_FULL]
+
+# Create and launch the interface using get_app utility
+demo = get_app(
+    models=GEMINI_MODELS_FULL,  # Use the full names with prefix
+    default_model=GEMINI_MODELS_FULL[-1],
+    dropdown_label="Select Gemini Model",
+    choices=GEMINI_MODELS_DISPLAY,  # Display names without prefix
+    src=ai_gradio.registry,
+    fill_height=True,
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_gemini_camera.py

@@ -0,0 +1,23 @@
+import ai_gradio
+
+from utils_ai_gradio import get_app
+
+# Get the Gemini models but keep their full names for loading
+GEMINI_MODELS_FULL = [k for k in ai_gradio.registry if k.startswith("gemini:")]
+
+# Create display names without the prefix
+GEMINI_MODELS_DISPLAY = [k.replace("gemini:", "") for k in GEMINI_MODELS_FULL]
+
+# Create and launch the interface using get_app utility
+demo = get_app(
+    models=GEMINI_MODELS_FULL,  # Use the full names with prefix
+    default_model=GEMINI_MODELS_FULL[-2],
+    dropdown_label="Select Gemini Model",
+    choices=GEMINI_MODELS_DISPLAY,  # Display names without prefix
+    src=ai_gradio.registry,
+    camera=True,
+    fill_height=True,
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_gemini_coder.py

@@ -0,0 +1,23 @@
+import ai_gradio
+
+from utils_ai_gradio import get_app
+
+# Get the Gemini models but keep their full names for loading
+GEMINI_MODELS_FULL = [k for k in ai_gradio.registry if k.startswith("gemini:")]
+
+# Create display names without the prefix
+GEMINI_MODELS_DISPLAY = [k.replace("gemini:", "") for k in GEMINI_MODELS_FULL]
+
+# Create and launch the interface using get_app utility
+demo = get_app(
+    models=GEMINI_MODELS_FULL,  # Use the full names with prefix
+    default_model=GEMINI_MODELS_FULL[-1],
+    dropdown_label="Select Gemini Model",
+    choices=GEMINI_MODELS_DISPLAY,  # Display names without prefix
+    src=ai_gradio.registry,
+    fill_height=True,
+    coder=True,
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_gemini_voice.py

@@ -0,0 +1,23 @@
+import ai_gradio
+
+from utils_ai_gradio import get_app
+
+# Get the Gemini models but keep their full names for loading
+GEMINI_MODELS_FULL = [k for k in ai_gradio.registry if k.startswith("gemini:")]
+
+# Create display names without the prefix
+GEMINI_MODELS_DISPLAY = [k.replace("gemini:", "") for k in GEMINI_MODELS_FULL]
+
+# Create and launch the interface using get_app utility
+demo = get_app(
+    models=GEMINI_MODELS_FULL,  # Use the full names with prefix
+    default_model=GEMINI_MODELS_FULL[-2],
+    dropdown_label="Select Gemini Model",
+    choices=GEMINI_MODELS_DISPLAY,  # Display names without prefix
+    src=ai_gradio.registry,
+    enable_voice=True,
+    fill_height=True,
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_groq.py

@@ -0,0 +1,21 @@
+import ai_gradio
+
+from utils_ai_gradio import get_app
+
+# Get the Groq models from the registry
+GROQ_MODELS_FULL = [k for k in ai_gradio.registry.keys() if k.startswith("groq:")]
+
+# Create display names without the prefix
+GROQ_MODELS_DISPLAY = [k.replace("groq:", "") for k in GROQ_MODELS_FULL]
+
+demo = get_app(
+    models=GROQ_MODELS_FULL,
+    default_model=GROQ_MODELS_FULL[-2],
+    src=ai_gradio.registry,
+    dropdown_label="Select Groq Model",
+    choices=GROQ_MODELS_DISPLAY,
+    fill_height=True,
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_groq_coder.py

@@ -0,0 +1,23 @@
+import ai_gradio
+
+from utils_ai_gradio import get_app
+
+# Get the Groq models but keep their full names for loading
+GROQ_MODELS_FULL = [k for k in ai_gradio.registry.keys() if k.startswith("groq:")]
+
+# Create display names without the prefix
+GROQ_MODELS_DISPLAY = [k.replace("groq:", "") for k in GROQ_MODELS_FULL]
+
+# Create and launch the interface using get_app utility
+demo = get_app(
+    models=GROQ_MODELS_FULL,  # Use the full names with prefix
+    default_model=GROQ_MODELS_FULL[-1],
+    dropdown_label="Select Groq Model",
+    choices=GROQ_MODELS_DISPLAY,  # Display names without prefix
+    fill_height=True,
+    coder=True,
+)
+
+
+if __name__ == "__main__":
+    demo.launch()

app_hf.py

@@ -0,0 +1,17 @@
+from utils import get_app
+
+demo = get_app(
+    models=[
+        "microsoft/Phi-3.5-mini-instruct",
+        "HuggingFaceTB/SmolLM2-1.7B-Instruct",
+        "google/gemma-2-2b-it",
+        "openai-community/gpt2",
+        "microsoft/phi-2",
+        "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+    ],
+    default_model="HuggingFaceTB/SmolLM2-1.7B-Instruct",
+    src="models",
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_huggingface.py

@@ -0,0 +1,67 @@
+import gradio as gr
+from gradio_client import Client, handle_file
+
+MODELS = {"SmolVLM-Instruct": "akhaliq/SmolVLM-Instruct"}
+
+
+def create_chat_fn(client):
+    def chat(message, history):
+        # Extract text and files from the message
+        text = message.get("text", "")
+        files = message.get("files", [])
+
+        # Handle file uploads if present
+        processed_files = [handle_file(f) for f in files]
+
+        response = client.predict(
+            message={"text": text, "files": processed_files},
+            system_prompt="You are a helpful AI assistant.",
+            temperature=0.7,
+            max_new_tokens=1024,
+            top_k=40,
+            repetition_penalty=1.1,
+            top_p=0.95,
+            api_name="/chat",
+        )
+        return response
+
+    return chat
+
+
+def set_client_for_session(model_name, request: gr.Request):
+    headers = {}
+    if request and hasattr(request, "headers"):
+        x_ip_token = request.headers.get("x-ip-token")
+        if x_ip_token:
+            headers["X-IP-Token"] = x_ip_token
+
+    return Client(MODELS[model_name], headers=headers)
+
+
+def safe_chat_fn(message, history, client):
+    if client is None:
+        return "Error: Client not initialized. Please refresh the page."
+    try:
+        return create_chat_fn(client)(message, history)
+    except Exception as e:
+        print(f"Error during chat: {e!s}")
+        return f"Error during chat: {e!s}"
+
+
+with gr.Blocks() as demo:
+    client = gr.State()
+
+    model_dropdown = gr.Dropdown(
+        choices=list(MODELS.keys()), value="SmolVLM-Instruct", label="Select Model", interactive=True
+    )
+
+    chat_interface = gr.ChatInterface(fn=safe_chat_fn, additional_inputs=[client], multimodal=True)
+
+    # Update client when model changes
+    model_dropdown.change(fn=set_client_for_session, inputs=[model_dropdown], outputs=[client])
+
+    # Initialize client on page load
+    demo.load(fn=set_client_for_session, inputs=[gr.State("SmolVLM-Instruct")], outputs=[client])
+
+if __name__ == "__main__":
+    demo.launch()

app_hyperbolic.py

@@ -0,0 +1,19 @@
+import ai_gradio
+
+from utils_ai_gradio import get_app
+
+# Get the hyperbolic models but keep their full names for loading
+HYPERBOLIC_MODELS_FULL = [k for k in ai_gradio.registry.keys() if k.startswith("hyperbolic:")]
+
+# Create display names without the prefix
+HYPERBOLIC_MODELS_DISPLAY = [k.replace("hyperbolic:", "") for k in HYPERBOLIC_MODELS_FULL]
+
+
+# Create and launch the interface using get_app utility
+demo = get_app(
+    models=HYPERBOLIC_MODELS_FULL,  # Use the full names with prefix
+    default_model=HYPERBOLIC_MODELS_FULL[-1],
+    dropdown_label="Select Hyperbolic Model",
+    choices=HYPERBOLIC_MODELS_DISPLAY,  # Display names without prefix
+    fill_height=True,
+)

app_hyperbolic_coder.py

@@ -0,0 +1,20 @@
+import ai_gradio
+
+from utils_ai_gradio import get_app
+
+# Get the hyperbolic models but keep their full names for loading
+HYPERBOLIC_MODELS_FULL = [k for k in ai_gradio.registry.keys() if k.startswith("hyperbolic:")]
+
+# Create display names without the prefix
+HYPERBOLIC_MODELS_DISPLAY = [k.replace("hyperbolic:", "") for k in HYPERBOLIC_MODELS_FULL]
+
+
+# Create and launch the interface using get_app utility
+demo = get_app(
+    models=HYPERBOLIC_MODELS_FULL,  # Use the full names with prefix
+    default_model=HYPERBOLIC_MODELS_FULL[-1],
+    dropdown_label="Select Hyperbolic Model",
+    choices=HYPERBOLIC_MODELS_DISPLAY,  # Display names without prefix
+    fill_height=True,
+    coder=True,
+)

app_langchain.py

@@ -0,0 +1,23 @@
+import ai_gradio
+
+from utils_ai_gradio import get_app
+
+# Get the hyperbolic models but keep their full names for loading
+LANGCHAIN_MODELS_FULL = [k for k in ai_gradio.registry.keys() if k.startswith("langchain:")]
+
+# Create display names without the prefix
+LANGCHAIN_MODELS_DISPLAY = [k.replace("langchain:", "") for k in LANGCHAIN_MODELS_FULL]
+
+
+# Create and launch the interface using get_app utility
+demo = get_app(
+    models=LANGCHAIN_MODELS_FULL,  # Use the full names with prefix
+    default_model=LANGCHAIN_MODELS_FULL[0],
+    dropdown_label="Select Langchain Model",
+    choices=LANGCHAIN_MODELS_DISPLAY,  # Display names without prefix
+    fill_height=True,
+)
+
+if __name__ == "__main__":
+    demo.launch()
+

app_lumaai.py

@@ -0,0 +1,7 @@
+import gradio as gr
+import lumaai_gradio
+
+demo = gr.load(
+    name="dream-machine",
+    src=lumaai_gradio.registry,
+)

app_marco_o1.py

@@ -0,0 +1,12 @@
+import gradio as gr
+import spaces
+import transformers_gradio
+
+demo = gr.load(name="AIDC-AI/Marco-o1", src=transformers_gradio.registry)
+demo.fn = spaces.GPU()(demo.fn)
+
+for fn in demo.fns.values():
+    fn.api_name = False
+
+if __name__ == "__main__":
+    demo.launch()

app_meta.py

@@ -0,0 +1,6 @@
+import gradio as gr
+
+demo = gr.load("models/meta-llama/Llama-3.3-70B-Instruct")
+
+if __name__ == "__main__":
+    demo.launch()

app_mindsearch.py

@@ -0,0 +1,12 @@
+import gradio as gr
+
+# Load the Gradio space
+demo = gr.load(name="internlm/MindSearch", src="spaces")
+
+# Disable API access for all functions
+if hasattr(demo, "fns"):
+    for fn in demo.fns.values():
+        fn.api_name = False
+
+if __name__ == "__main__":
+    demo.launch()

app_minimax.py

@@ -0,0 +1,22 @@
+import ai_gradio
+
+from utils_ai_gradio import get_app
+
+# Get the hyperbolic models but keep their full names for loading
+MINIMAX_MODELS_FULL = [k for k in ai_gradio.registry.keys() if k.startswith("minimax:")]
+
+# Create display names without the prefix
+MINIMAX_MODELS_DISPLAY = [k.replace("minimax:", "") for k in MINIMAX_MODELS_FULL]
+
+
+# Create and launch the interface using get_app utility
+demo = get_app(
+    models=MINIMAX_MODELS_FULL,  # Use the full names with prefix
+    default_model=MINIMAX_MODELS_FULL[0],
+    dropdown_label="Select Minimax Model",
+    choices=MINIMAX_MODELS_DISPLAY,  # Display names without prefix
+    fill_height=True,
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_minimax_coder.py

@@ -0,0 +1,23 @@
+import ai_gradio
+
+from utils_ai_gradio import get_app
+
+# Get the hyperbolic models but keep their full names for loading
+MINIMAX_MODELS_FULL = [k for k in ai_gradio.registry.keys() if k.startswith("minimax:")]
+
+# Create display names without the prefix
+MINIMAX_MODELS_DISPLAY = [k.replace("minimax:", "") for k in MINIMAX_MODELS_FULL]
+
+
+# Create and launch the interface using get_app utility
+demo = get_app(
+    models=MINIMAX_MODELS_FULL,  # Use the full names with prefix
+    default_model=MINIMAX_MODELS_FULL[0],
+    dropdown_label="Select Minimax Model",
+    choices=MINIMAX_MODELS_DISPLAY,  # Display names without prefix
+    fill_height=True,
+    coder=True
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_mistral.py

@@ -0,0 +1,23 @@
+import ai_gradio
+
+from utils_ai_gradio import get_app
+
+# Get the mistral models but keep their full names for loading
+MISTRAL_MODELS_FULL = [k for k in ai_gradio.registry.keys() if k.startswith("mistral:")]
+
+# Create display names without the prefix
+MISTRAL_MODELS_DISPLAY = [k.replace("mistral:", "") for k in MISTRAL_MODELS_FULL]
+
+
+# Create and launch the interface using get_app utility
+demo = get_app(
+    models=MISTRAL_MODELS_FULL,  # Use the full names with prefix
+    default_model=MISTRAL_MODELS_FULL[5],
+    dropdown_label="Select Mistral Model",
+    choices=MISTRAL_MODELS_DISPLAY,  # Display names without prefix
+    fill_height=True,
+    coder=True
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_moondream.py

@@ -0,0 +1,13 @@
+import gradio as gr
+
+# Load the Gradio space
+demo = gr.load(name="akhaliq/moondream", src="spaces")
+
+
+# Disable API access for all functions
+if hasattr(demo, "fns"):
+    for fn in demo.fns.values():
+        fn.api_name = False
+
+if __name__ == "__main__":
+    demo.launch()

app_nvidia.py

@@ -0,0 +1,22 @@
+import ai_gradio
+
+from utils_ai_gradio import get_app
+
+# Get the nvidia models but keep their full names for loading
+NVIDIA_MODELS_FULL = [k for k in ai_gradio.registry.keys() if k.startswith("nvidia:")]
+
+# Create display names without the prefix
+NVIDIA_MODELS_DISPLAY = [k.replace("nvidia:", "") for k in NVIDIA_MODELS_FULL]
+
+
+# Create and launch the interface using get_app utility
+demo = get_app(
+    models=NVIDIA_MODELS_FULL,  # Use the full names with prefix
+    default_model=NVIDIA_MODELS_FULL[0],
+    dropdown_label="Select Nvidia Model",
+    choices=NVIDIA_MODELS_DISPLAY,  # Display names without prefix
+    fill_height=True,
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_omini.py

@@ -0,0 +1,10 @@
+import gradio as gr
+
+# Load the Gradio space
+demo = gr.load(name="Yuanshi/OminiControl", src="spaces")
+
+
+# Disable API access for all functions
+if hasattr(demo, "fns"):
+    for fn in demo.fns.values():
+        fn.api_name = False

app_openai.py

@@ -0,0 +1,21 @@
+import ai_gradio
+
+from utils_ai_gradio import get_app
+
+# Get the OpenAI models but keep their full names for loading
+OPENAI_MODELS_FULL = [k for k in ai_gradio.registry.keys() if k.startswith("openai:")]
+
+# Create display names without the prefix
+OPENAI_MODELS_DISPLAY = [k.replace("openai:", "") for k in OPENAI_MODELS_FULL]
+
+# Create and launch the interface using get_app utility
+demo = get_app(
+    models=OPENAI_MODELS_FULL,  # Use the full names with prefix
+    default_model=OPENAI_MODELS_FULL[-1],
+    dropdown_label="Select OpenAI Model",
+    choices=OPENAI_MODELS_DISPLAY,  # Display names without prefix
+    fill_height=True,
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_openai_coder.py

@@ -0,0 +1,22 @@
+import ai_gradio
+
+from utils_ai_gradio import get_app
+
+# Get the OpenAI models but keep their full names for loading
+OPENAI_MODELS_FULL = [k for k in ai_gradio.registry.keys() if k.startswith("openai:")]
+
+# Create display names without the prefix
+OPENAI_MODELS_DISPLAY = [k.replace("openai:", "") for k in OPENAI_MODELS_FULL]
+
+# Create and launch the interface using get_app utility
+demo = get_app(
+    models=OPENAI_MODELS_FULL,  # Use the full names with prefix
+    default_model=OPENAI_MODELS_FULL[5],
+    dropdown_label="Select OpenAI Model",
+    choices=OPENAI_MODELS_DISPLAY,  # Display names without prefix
+    fill_height=True,
+    coder=True,
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_openai_voice.py

@@ -0,0 +1,23 @@
+import os
+
+import openai_gradio
+
+from utils import get_app
+
+demo = get_app(
+    models=[
+        "gpt-4o-realtime-preview",
+        "gpt-4o-realtime-preview-2024-12-17",
+        "gpt-4o-realtime-preview-2024-10-01",
+        "gpt-4o-mini-realtime-preview",
+        "gpt-4o-mini-realtime-preview-2024-12-17",
+    ],
+    default_model="gpt-4o-mini-realtime-preview-2024-12-17",
+    src=openai_gradio.registry,
+    accept_token=not os.getenv("OPENAI_API_KEY"),
+    twilio_sid=os.getenv("TWILIO_SID_OPENAI"),
+    twilio_token=os.getenv("TWILIO_AUTH_OPENAI"),
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_paligemma.py

@@ -0,0 +1,78 @@
+import gradio as gr
+from gradio_client import Client, handle_file
+
+MODELS = {"Paligemma-10B": "akhaliq/paligemma2-10b-ft-docci-448"}
+
+
+def create_chat_fn(client, system_prompt, temperature, max_tokens, top_k, rep_penalty, top_p):
+    def chat(message, history):
+        text = message.get("text", "")
+        files = message.get("files", [])
+        processed_files = [handle_file(f) for f in files]
+
+        response = client.predict(
+            message={"text": text, "files": processed_files},
+            system_prompt=system_prompt,
+            temperature=temperature,
+            max_new_tokens=max_tokens,
+            top_k=top_k,
+            repetition_penalty=rep_penalty,
+            top_p=top_p,
+            api_name="/chat",
+        )
+        return response
+
+    return chat
+
+
+def set_client_for_session(model_name, request: gr.Request):
+    headers = {}
+    if request and hasattr(request, "headers"):
+        x_ip_token = request.headers.get("x-ip-token")
+        if x_ip_token:
+            headers["X-IP-Token"] = x_ip_token
+
+    return Client(MODELS[model_name], headers=headers)
+
+
+def safe_chat_fn(message, history, client, system_prompt, temperature, max_tokens, top_k, rep_penalty, top_p):
+    if client is None:
+        return "Error: Client not initialized. Please refresh the page."
+    try:
+        return create_chat_fn(client, system_prompt, temperature, max_tokens, top_k, rep_penalty, top_p)(
+            message, history
+        )
+    except Exception as e:
+        print(f"Error during chat: {e!s}")
+        return f"Error during chat: {e!s}"
+
+
+with gr.Blocks() as demo:
+    client = gr.State()
+
+    with gr.Accordion("Advanced Settings", open=False):
+        system_prompt = gr.Textbox(value="You are a helpful AI assistant.", label="System Prompt")
+        with gr.Row():
+            temperature = gr.Slider(minimum=0.0, maximum=2.0, value=0.7, label="Temperature")
+            top_p = gr.Slider(minimum=0.0, maximum=1.0, value=0.95, label="Top P")
+        with gr.Row():
+            top_k = gr.Slider(minimum=1, maximum=100, value=40, step=1, label="Top K")
+            rep_penalty = gr.Slider(minimum=1.0, maximum=2.0, value=1.1, label="Repetition Penalty")
+        max_tokens = gr.Slider(minimum=64, maximum=4096, value=1024, step=64, label="Max Tokens")
+
+    chat_interface = gr.ChatInterface(
+        fn=safe_chat_fn,
+        additional_inputs=[client, system_prompt, temperature, max_tokens, top_k, rep_penalty, top_p],
+        multimodal=True,
+    )
+
+    # Initialize client on page load with default model
+    demo.load(fn=set_client_for_session, inputs=[gr.State("Paligemma-10B")], outputs=[client])  # Using default model
+
+# Move the API access check here, after demo is defined
+if hasattr(demo, "fns"):
+    for fn in demo.fns.values():
+        fn.api_name = False
+
+if __name__ == "__main__":
+    demo.launch()

app_perplexity.py

@@ -0,0 +1,23 @@
+import os
+
+import perplexity_gradio
+
+from utils import get_app
+
+demo = get_app(
+    models=[
+        "llama-3.1-sonar-large-128k-online",
+        "llama-3.1-sonar-small-128k-online",
+        "llama-3.1-sonar-huge-128k-online",
+        "llama-3.1-sonar-small-128k-chat",
+        "llama-3.1-sonar-large-128k-chat",
+        "llama-3.1-8b-instruct",
+        "llama-3.1-70b-instruct",
+    ],
+    default_model="llama-3.1-sonar-huge-128k-online",
+    src=perplexity_gradio.registry,
+    accept_token=not os.getenv("PERPLEXITY_API_KEY"),
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_playai.py

@@ -0,0 +1,10 @@
+import gradio as gr
+import playai_gradio
+
+demo = gr.load(
+    name="PlayDialog",
+    src=playai_gradio.registry,
+)
+
+for fn in demo.fns.values():
+    fn.api_name = False

app_qwen.py

@@ -0,0 +1,27 @@
+import os
+
+import dashscope_gradio
+
+from utils import get_app
+
+demo = get_app(
+    models=[
+        "qwen-turbo-latest",
+        "qwen-turbo",
+        "qwen-plus",
+        "qwen-max",
+        "qwen1.5-110b-chat",
+        "qwen1.5-72b-chat",
+        "qwen1.5-32b-chat",
+        "qwen1.5-14b-chat",
+        "qwen1.5-7b-chat",
+        "qwq-32b-preview",
+        "qvq-72b-preview",
+    ],
+    default_model="qvq-72b-preview",
+    src=dashscope_gradio.registry,
+    accept_token=not os.getenv("DASHSCOPE_API_KEY"),
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_replicate.py

@@ -0,0 +1,18 @@
+import replicate_gradio
+
+from utils import get_app
+
+demo = get_app(
+    models=[
+        "black-forest-labs/flux-depth-pro",
+        "black-forest-labs/flux-canny-pro",
+        "black-forest-labs/flux-fill-pro",
+        "black-forest-labs/flux-depth-dev",
+        "tencent/hunyuan-video:140176772be3b423d14fdaf5403e6d4e38b85646ccad0c3fd2ed07c211f0cad1",
+    ],
+    default_model="tencent/hunyuan-video:140176772be3b423d14fdaf5403e6d4e38b85646ccad0c3fd2ed07c211f0cad1",
+    src=replicate_gradio.registry,
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_sailor.py

@@ -0,0 +1,9 @@
+import gradio as gr
+import spaces
+import transformers_gradio
+
+demo = gr.load(name="sail/Sailor2-20B-Chat", src=transformers_gradio.registry)
+demo.fn = spaces.GPU()(demo.fn)
+
+for fn in demo.fns.values():
+    fn.api_name = False

app_sambanova.py

@@ -0,0 +1,28 @@
+import os
+
+import sambanova_gradio
+
+from utils import get_app
+
+demo = get_app(
+    models=[
+        "Meta-Llama-3.2-1B-Instruct",
+        "Meta-Llama-3.2-3B-Instruct",
+        "Llama-3.2-11B-Vision-Instruct",
+        "Llama-3.2-90B-Vision-Instruct",
+        "Meta-Llama-3.1-8B-Instruct",
+        "Meta-Llama-3.1-70B-Instruct",
+        "Meta-Llama-3.1-405B-Instruct",
+        "Qwen2.5-72B-Instruct",
+        "Qwen2.5-Coder-32B-Instruct",
+        "Meta-Llama-3.3-70B-Instruct",
+        "QwQ-32B-Preview",
+    ],
+    default_model="QwQ-32B-Preview",
+    src=sambanova_gradio.registry,
+    accept_token=not os.getenv("SAMBANOVA_API_KEY"),
+    multimodal=True,
+)
+
+if __name__ == "__main__":
+    demo.launch()

app_sambanova_qwen.py

@@ -0,0 +1,21 @@
+import os
+
+import sambanova_gradio
+
+from utils import get_app
+
+demo = get_app(
+    models=[
+        "Qwen2.5-Coder-0.5B-Instruct",
+        "Qwen2.5-0.5B-Instruct",
+        "Qwen2.5-Coder-32B-Instruct",
+        "Qwen2.5-72B-Instruct",
+    ],
+    default_model="Qwen2.5-Coder-32B-Instruct",
+    src=sambanova_gradio.registry,
+    accept_token=not os.getenv("SAMBANOVA_API_KEY"),
+    multimodal=True,
+)
+
+if __name__ == "__main__":
+    demo.launch()