Merge branch 'main' of https://github.com/NexaAI/nexaai-sdk-cpp into …

…david/bugfix

Dockerfile

@@ -0,0 +1,24 @@
+# Use a base image that includes Miniconda
+FROM continuumio/miniconda3
+
+# Set the working directory in the container
+WORKDIR /app
+
+RUN apt-get update && apt-get install -y cmake g++
+# Copy the environment.yml file into the container at /app
+COPY pyproject.toml CMakeLists.txt requirements.txt README.md ./
+COPY dependency ./dependency
+
+# Install the conda environment
+RUN conda create -n nexa python=3.10 -y
+RUN /bin/bash -c "source activate nexa && pip install -r requirements.txt && pip install -e ."
+
+# Activate the environment
+RUN echo "source activate nexa" > ~/.bashrc
+ENV PATH /opt/conda/envs/nexa/bin:$PATH
+
+# Copy your application code to the container
+COPY . .
+
+# Set the command to activate the environment and start your application
+CMD ["bash", "-c", "source activate nexa && python -m nexa.cli.entry gen-text gemma"]

README.md

@@ -24,7 +24,7 @@ Detailed API documentation is available [here](docs/index.html).
 
 ## Installation
 
-**GPU version(optional)**
+### GPU version(optional)
 
 check if you have GPU acceleration (torch required)
 <details>
@@ -38,11 +38,11 @@ check if you have GPU acceleration (torch required)
   if True
 
   ```
-  CMAKE_ARGS="-DGGML_CUDA=on -DSD_CUBLAS=ON" pip install nexaai-gpu
+  CMAKE_ARGS="-DGGML_CUDA=on -DSD_CUBLAS=ON" pip install nexaai
   ```
   Or you prefer to install our pre-built wheel:
   ```bash
-  pip install nexaai-cuda --index-url https://nexaai.github.io/nexa-sdk/whl/cu124 --extra-index-url https://pypi.org/simple
+  pip install nexaai --index-url https://nexaai.github.io/nexa-sdk/whl/cu124 --extra-index-url https://pypi.org/simple
   ```
 </details>
 <details>
@@ -52,24 +52,15 @@ check if you have GPU acceleration (torch required)
   if True:
 
   ```
-  CMAKE_ARGS="-DGGML_METAL=on -DSD_METAL=ON" pip install nexaai-gpu
+  CMAKE_ARGS="-DGGML_METAL=on -DSD_METAL=ON" pip install nexaai
   ```
   Or you prefer to install our pre-built wheel:
   ```bash
-  pip install nexaai-metal --index-url https://nexaai.github.io/nexa-sdk/whl/metal --extra-index-url https://pypi.org/simple
+  pip install nexaai --index-url https://nexaai.github.io/nexa-sdk/whl/metal --extra-index-url https://pypi.org/simple
   ```
 </details>
 
-<details>
-  <summary>AMD graphics card:</summary>
-
-
-  ```
-  CMAKE_ARGS="-DGGML_HIPBLAS=on" pip install nexaai-gpu
-  ```
-</details>
-
-**CPU version**
+### CPU version
 
 <details>
   <summary>Mac with Intel chips</summary>
@@ -92,6 +83,22 @@ Or you prefer to install the pre-built wheel:
 pip install nexaai --index-url https://nexaai.github.io/nexa-sdk/whl/cpu --extra-index-url https://pypi.org/simple
 ```
 
+### Docker Usage
+Note: Docker doesn't support GPU acceleration
+
+`docker pull nexa4ai/sdk:latest`
+
+replace following placeholder with your path and command
+
+`docker run -v <your_model_dir>:/model -it nexa4ai/sdk:latest [nexa_command] [your_model_relative_path]`
+
+Example:
+
+`docker run -v /home/ubuntu/.cache/nexa/hub/official:/model -it nexa4ai/sdk:latest nexa gen-text /model/Phi-3-mini-128k-instruct/q4_0.gguf`
+
+will create an interactive session with text generation
+```
+
 ## Nexa CLI commands
 
 ## Model Commands

nexa/onnx/nexa_inference_image.py

@@ -30,8 +30,8 @@ class NexaImageInference:
     A class used for loading image models and running image generation.
 
     Methods:
-    run: Run the image generation loop.
-    run_streamlit: Run the Streamlit UI.
+        run: Run the image generation loop.
+        run_streamlit: Run the Streamlit UI.
 
     Args:
     model_path (str): Path or identifier for the model in Nexa Model Hub.

pyproject.toml

@@ -78,6 +78,7 @@ sdist.exclude = [".github", "build", "dist", "nexa.egg-info", "dependency/llama.
 build.verbose = true
 cmake.build-type = "Release"
 cmake.version = ">=3.16"
+cmake.args = ["-DCMAKE_CXX_FLAGS=-fopenmp"]
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]