sphinx + .nojekyll in docs(<-docs/build/html)

docs/.buildinfo

@@ -0,0 +1,4 @@
+# Sphinx build info version 1
+# This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
+config: cb535833a47a005a6969e1994cc1d26c
+tags: 645f666f9bcd5a90fca523b33c5a78b7

docs/_sources/agent.rst.txt

@@ -0,0 +1,46 @@
+Agent Interactions
+==================
+
+Multi-turn Conversation
+-----------------------
+
+.. code-block:: python
+
+    from phi_3_vision_mlx import Agent
+
+    # Create an instance of the Agent
+    agent = Agent()
+
+    # First interaction: Analyze an image
+    agent('Analyze this image and describe the architectural style:', 'https://images.metmuseum.org/CRDImages/rl/original/DP-19531-075.jpg')
+
+    # Second interaction: Follow-up question
+    agent('What historical period does this architecture likely belong to?')
+
+    # End the conversation
+    agent.end()
+
+Generative Feedback Loop
+------------------------
+
+.. code-block:: python
+
+    # Ask the agent to generate and execute code to create a plot
+    agent('Plot a Lissajous Curve.')
+
+    # Ask the agent to modify the generated code and create a new plot
+    agent('Modify the code to plot 3:4 frequency')
+    agent.end()
+
+External API Tool Use
+---------------------
+
+.. code-block:: python
+
+    # Request the agent to generate an image
+    agent('Draw "A perfectly red apple, 32k HDR, studio lighting"')
+    agent.end()
+
+    # Request the agent to convert text to speech
+    agent('Speak "People say nothing is impossible, but I do nothing every day."')
+    agent.end()

docs/_sources/benchmark.rst.txt

@@ -0,0 +1,8 @@
+Benchmark
+=================
+
+.. code-block:: python
+
+    from phi_3_vision_mlx import benchmark
+
+    benchmark()

docs/_sources/generate.rst.txt

@@ -0,0 +1,39 @@
+Text Generation
+===============
+
+Visual Question Answering
+-------------------------
+
+.. code-block:: python
+
+    generate('What is shown in this image?', 'https://collectionapi.metmuseum.org/api/collection/v1/iiif/344291/725918/main-image')
+
+Batch Text Generation
+---------------------
+
+.. code-block:: python
+
+    prompts = [
+        "Explain the key concepts of quantum computing and provide a Rust code example demonstrating quantum superposition.",
+        "Write a poem about the first snowfall of the year.",
+        "Summarize the major events of the French Revolution.",
+        "Describe a bustling alien marketplace on a distant planet with unique goods and creatures."
+        "Implement a basic encryption algorithm in Python.",
+    ]
+
+    # Generate responses using Phi-3-Vision (multimodal model)
+    generate(prompts, max_tokens=100)
+
+    # Generate responses using Phi-3-Mini-128K (language-only model)
+    generate(prompts, max_tokens=100, blind_model=True)
+
+Model and Cache Quantization
+----------------------------
+
+.. code-block:: python
+
+    # Model quantization
+    generate("Describe the water cycle.", quantize_model=True)
+
+    # Cache quantization
+    generate("Explain quantum computing.", quantize_cache=True)

docs/_sources/index.rst.txt

@@ -0,0 +1,66 @@
+.. phi-3-vision-mlx documentation master file, created by
+   sphinx-quickstart on Sun Jul  7 23:52:18 2024.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+Welcome to phi-3-vision-mlx's documentation!
+============================================
+
+Phi-3-MLX is a versatile AI framework that leverages both the Phi-3-Vision multimodal model and the recently updated Phi-3-Mini-128K language model, optimized for Apple Silicon using the MLX framework.
+
+`View the project on GitHub <https://github.com/JosefAlbers/Phi-3-Vision-MLX>`_
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Contents
+
+   install
+   generate
+   train
+   agent
+   toolchain
+   benchmark
+
+.. toctree::
+   :maxdepth: 1
+   :caption: API Reference
+
+   module
+
+Features
+--------
+
+- Support for the newly updated Phi-3-Mini-128K (language-only) model
+- Integration with Phi-3-Vision (multimodal) model
+- Optimized performance on Apple Silicon using MLX
+- Batched generation for processing multiple prompts
+- Flexible agent system for various AI tasks
+- Custom toolchains for specialized workflows
+- Model quantization for improved efficiency
+- LoRA fine-tuning capabilities
+- API integration for extended functionality (e.g., image generation, text-to-speech)
+
+Recent Updates: Phi-3 Mini Improvements
+---------------------------------------
+
+Microsoft has recently released significant updates to the Phi-3 Mini model, dramatically improving its capabilities:
+
+- Substantially enhanced code understanding in Python, C++, Rust, and TypeScript
+- Improved post-training for better-structured output
+- Enhanced multi-turn instruction following
+- Added support for the `<|system|>` tag
+- Improved reasoning and long-context understanding
+
+For detailed benchmark results, please refer to the tables in the README.
+
+License
+-------
+
+This project is licensed under the MIT License.
+
+Citation
+--------
+
+.. image:: https://zenodo.org/badge/806709541.svg
+   :target: https://zenodo.org/doi/10.5281/zenodo.11403221
+   :alt: DOI

docs/_sources/install.rst.txt

@@ -0,0 +1,15 @@
+Installation
+============
+
+You can install and launch Phi-3-MLX from the command line:
+
+.. code-block:: bash
+
+    pip install phi-3-vision-mlx
+    phi3v
+
+To use the library in a Python script:
+
+.. code-block:: python
+
+    from phi_3_vision_mlx import generate

docs/_sources/module.rst.txt

@@ -0,0 +1,57 @@
+
+Classes
+-------
+
+Agent
+^^^^^
+
+.. autoclass:: phi_3_vision_mlx.Agent
+   :no-members:
+
+Functions
+---------
+
+add_code
+^^^^^^^^
+
+.. autofunction:: phi_3_vision_mlx.add_code
+
+benchmark
+^^^^^^^^^
+
+.. autofunction:: phi_3_vision_mlx.benchmark
+
+chatui
+^^^^^^
+
+.. autofunction:: phi_3_vision_mlx.chatui
+
+execute
+^^^^^^^
+
+.. autofunction:: phi_3_vision_mlx.execute
+
+generate
+^^^^^^^^
+
+.. autofunction:: phi_3_vision_mlx.generate
+
+get_api
+^^^^^^^
+
+.. autofunction:: phi_3_vision_mlx.get_api
+
+load
+^^^^
+
+.. autofunction:: phi_3_vision_mlx.load
+
+test_lora
+^^^^^^^^^
+
+.. autofunction:: phi_3_vision_mlx.test_lora
+
+train_lora
+^^^^^^^^^^
+
+.. autofunction:: phi_3_vision_mlx.train_lora

docs/_sources/toolchain.rst.txt

@@ -0,0 +1,66 @@
+Custom Toolchains
+=================
+
+Example 1: In-Context Learning Agent
+------------------------------------
+
+.. code-block:: python
+
+    from phi_3_vision_mlx import _load_text
+
+    # Create a custom tool named 'add_text'
+    def add_text(prompt):
+        prompt, path = prompt.split('@')
+        return f'{_load_text(path)}\n<|end|>\n<|user|>{prompt}'
+
+    # Define the toolchain as a string
+    toolchain = """
+        prompt = add_text(prompt)
+        responses = generate(prompt, images)
+        """
+
+    # Create an Agent instance with the custom toolchain
+    agent = Agent(toolchain, early_stop=100)
+
+    # Run the agent
+    agent('How to inspect API endpoints? @https://raw.githubusercontent.com/gradio-app/gradio/main/guides/08_gradio-clients-and-lite/01_getting-started-with-the-python-client.md')
+
+Example 2: Retrieval Augmented Coding Agent
+-------------------------------------------
+
+.. code-block:: python
+
+    from phi_3_vision_mlx import VDB
+    import datasets
+
+    # Simulate user input
+    user_input = 'Comparison of Sortino Ratio for Bitcoin and Ethereum.'
+
+    # Create a custom RAG tool
+    def rag(prompt, repo_id="JosefAlbers/sharegpt_python_mlx", n_topk=1):
+        ds = datasets.load_dataset(repo_id, split='train')
+        vdb = VDB(ds)
+        context = vdb(prompt, n_topk)[0][0]
+        return f'{context}\n<|end|>\n<|user|>Plot: {prompt}'
+
+    # Define the toolchain
+    toolchain_plot = """
+        prompt = rag(prompt)
+        responses = generate(prompt, images)
+        files = execute(responses, step)
+        """
+
+    # Create an Agent instance with the RAG toolchain
+    agent = Agent(toolchain_plot, False)
+
+    # Run the agent with the user input
+    _, images = agent(user_input)
+
+Example 3: Multi-Agent Interaction
+----------------------------------
+
+.. code-block:: python
+
+    # Continued from Example 2 above
+    agent_writer = Agent(early_stop=100)
+    agent_writer(f'Write a stock analysis report on: {user_input}', images)

docs/_sources/train.rst.txt

@@ -0,0 +1,46 @@
+LoRA Fine-tuning
+================
+
+Training a LoRA Adapter
+-----------------------
+
+.. code-block:: python
+
+    from phi_3_vision_mlx import train_lora
+
+    train_lora(
+        lora_layers=5,  # Number of layers to apply LoRA
+        lora_rank=16,   # Rank of the LoRA adaptation
+        epochs=10,      # Number of training epochs
+        lr=1e-4,        # Learning rate
+        warmup=0.5,     # Fraction of steps for learning rate warmup
+        dataset_path="JosefAlbers/akemiH_MedQA_Reason"
+    )
+
+Generating Text with LoRA
+-------------------------
+
+.. code-block:: python
+
+    generate("Describe the potential applications of CRISPR gene editing in medicine.",
+        blind_model=True,
+        quantize_model=True,
+        use_adapter=True)
+
+Comparing LoRA Adapters
+-----------------------
+
+.. code-block:: python
+
+    from phi_3_vision_mlx import test_lora
+
+    # Test model without LoRA adapter
+    test_lora(adapter_path=None)
+    # Output score: 0.6 (6/10)
+
+    # Test model with the trained LoRA adapter (using default path)
+    test_lora(adapter_path=True)
+    # Output score: 0.8 (8/10)
+
+    # Test model with a specific LoRA adapter path
+    test_lora(adapter_path="/path/to/your/lora/adapter")