0.3.12

.github/workflows/upload-pypi-dev.yml

@@ -1,4 +1,4 @@
-name: Upload Python package to PyPI as dev pre-release
+name: Upload Python package to PyPI as dev release and build/push Docker image.
 
 on:
   workflow_dispatch:
@@ -39,3 +39,48 @@ jobs:
           git add pyproject.toml
           git commit -m "[fix] bump prerelease version in pyproject.toml"
           git push
+
+      # Wait for PyPI to update
+      - name: Wait for PyPI to update
+        run: |
+          VERSION=$(poetry version --short)
+          echo "Checking for llmstudio==$VERSION on PyPI..."
+          for i in {1..10}; do
+            if python -m pip install llmstudio==${VERSION} --dry-run >/dev/null 2>&1; then
+              echo "Package llmstudio==${VERSION} is available on PyPI."
+              break
+            else
+              echo "Package llmstudio==${VERSION} not available yet. Waiting 15 seconds..."
+              sleep 15
+            fi
+            if [ $i -eq 10 ]; then
+              echo "Package did not become available in time."
+              exit 1
+            fi
+          done
+
+      # Docker build and push section
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+
+      - name: Extract version for tagging Docker image
+        id: get_version
+        run: |
+          echo "VERSION=$(poetry version --short)" >> $GITHUB_ENV
+
+      - name: Build and tag Docker image
+        run: |
+          docker build \
+            --build-arg LLMSTUDIO_VERSION=${{ env.VERSION }} \
+            -t tensoropsai/llmstudio:${{ env.VERSION }} \
+            .
+
+      - name: Push Docker image to Docker Hub
+        run: |
+          docker push tensoropsai/llmstudio:${{ env.VERSION }}

.github/workflows/upload-pypi.yml

@@ -1,4 +1,4 @@
-name: Upload Python package to PyPI
+name: Upload Python package to PyPI and build/push Docker images.
 
 on:
   push:
@@ -11,23 +11,77 @@ jobs:
   deploy:
     runs-on: ubuntu-latest
     steps:
+      # Checkout the code
       - name: Checkout code
         uses: actions/checkout@v2
 
+      # Set up Python environment
       - name: Set up Python
         uses: actions/setup-python@v2
         with:
           python-version: "3.x"
 
+      # Install Poetry
       - name: Install Poetry
         run: |
           curl -sSL https://install.python-poetry.org | python3 -
 
+      # Configure Poetry with PyPI token
       - name: Configure Poetry
         run: |
           poetry config pypi-token.pypi ${{ secrets.PYPI_API_TOKEN }}
 
+      # Build and publish package to PyPI
       - name: Build and publish to PyPI
         run: |
           poetry build
           poetry publish
+
+      # Extract the new version number from pyproject.toml
+      - name: Extract version for tagging Docker image
+        run: |
+          echo "VERSION=$(poetry version --short)" >> $GITHUB_ENV
+
+      # Wait for the package to become available on PyPI
+      - name: Wait for PyPI to update
+        run: |
+          echo "Checking for llmstudio==${{ env.VERSION }} on PyPI..."
+          for i in {1..10}; do
+            if python -m pip install llmstudio==${{ env.VERSION }} --dry-run >/dev/null 2>&1; then
+              echo "Package llmstudio==${{ env.VERSION }} is available on PyPI."
+              break
+            else
+              echo "Package llmstudio==${{ env.VERSION }} not available yet. Waiting 15 seconds..."
+              sleep 15
+            fi
+            if [ $i -eq 10 ]; then
+              echo "Package did not become available in time."
+              exit 1
+            fi
+          done
+
+      # Set up Docker Buildx
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
+      # Log in to Docker Hub
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+
+      # Build and tag Docker images with both :latest and :[NEW_VERSION]
+      - name: Build and tag Docker images
+        run: |
+          docker build \
+            --build-arg LLMSTUDIO_VERSION=${{ env.VERSION }} \
+            -t tensoropsai/llmstudio:latest \
+            -t tensoropsai/llmstudio:${{ env.VERSION }} \
+            .
+
+      # Push both Docker images to Docker Hub
+      - name: Push Docker images to Docker Hub
+        run: |
+          docker push tensoropsai/llmstudio:${{ env.VERSION }}
+          docker push tensoropsai/llmstudio:latest

docs/how-to/build-a-tool-agent.mdx

@@ -0,0 +1,80 @@
+This guide outlines how to build a tool calling agent using Langchain + LLMstudio. 
+
+## 1. Set up your tools
+Start by defining the tools your agent is going to have access to.
+```python
+from langchain.tools import tool
+
+@tool
+def buy_ticket(destination: str):
+    """Use this to buy a ticket"""
+    return "Bought ticket number 270924"
+
+@tool
+def get_departure(ticket_number: str):
+    """Use this to fetch the departure time of a train"""
+    return "8:25 AM"
+```
+
+## 2. Setup your .env
+Create a `.env` file on the root of your project with the the credentials for the providers you want to use.
+
+<Tabs>
+    <Tab title="OpenAI">
+        ```
+        OPENAI_API_KEY="YOUR_API_KEY"
+        ```
+    </Tab>
+    <Tab title="VertexAI">
+        ```
+        GOOGLE_API_KEY="YOUR_API_KEY"
+        ```
+    </Tab>
+    <Tab title="Azure">
+        ```
+        AZURE_BASE_URL="YOUR_MODEL_ENDPOINT"
+        AZURE_API_KEY="YOUR_API_KEY"
+        ```
+    </Tab>
+  </Tabs>
+
+## 3. Set up your model using LLMstudio
+Use LLMstudio to choose the provider and model you want to use.
+<Tabs>
+    <Tab title="OpenAI">
+        ```python
+        model = ChatLLMstudio(model_id='openai/gpt-4o')
+        ```
+    </Tab>
+    <Tab title="VertexAI">
+        ```python
+        model = ChatLLMstudio(model_id='vertexai/gemini-1.5-flash')
+        ```
+    </Tab>
+    <Tab title="Azure">
+        ```python
+        model = ChatLLMstudio(model_id='azure/Meta-Llama-3.1-70B-Instruct')
+        ```
+    </Tab>
+  </Tabs>
+
+## 4. Build the agent
+Set up your agent and agent executor using Langchain.
+
+```python
+from langchain import hub
+from langchain.agents import AgentExecutor, create_openai_tools_agent
+
+prompt = hub.pull("hwchase17/openai-tools-agent")
+agent = create_openai_tools_agent(model, tools, prompt)
+agent_executor = AgentExecutor(agent=agent, tools=tools)
+
+input = "Can you buy me a ticket to madrid?"
+
+# Using with chat history
+agent_executor.invoke(
+    {
+        "input": input,
+    }
+)
+```

docs/how-to/deploy-on-gke/deploy-on-google-kubernetes-engine.mdx

@@ -0,0 +1,156 @@
+Learn how to deploy LLMstudio as a containerized application on Google Kubernetes Engine and make calls from a local repository.
+
+
+## Prerequisites
+To follow this guide you need to have the following set-up:
+
+- A **project** on google cloud platform.
+- **Kubernetes Engine** API enabled on your project.
+- **Kubernetes Engine Admin** role for the user performing the guide.
+
+## Deploy LLMstudio
+
+This example demonstrates a public deployment. For a private service accessible only within your enterprise infrastructure, deploy it within your own Virtual Private Cloud (VPC).
+<Steps>
+  <Step title="Navigate to Kubernetes Engine">
+    Begin by navigating to the Kubernetes Engine page.
+  </Step>
+  <Step title="Select Deploy">
+    Go to **Workloads** and **Create a new Deployment**.
+    <Frame>
+      <img src="how-to/deploy-on-gke/images/step-2.png" />
+    </Frame>
+  </Step>
+  <Step title="Name Your Deployment">
+    Rename your project. We will call the one in this guide **llmstudio-on-gcp**.
+    <Frame>
+      <img src="how-to/deploy-on-gke/images/step-3.png" />
+    </Frame>
+  </Step>
+  <Step title="Select Your Cluster">
+    Choose between **creating a new cluster** or **using an existing cluster**. 
+    For this guide, we will create a new cluster and use the default region.
+    <Frame>
+      <img src="how-to/deploy-on-gke/images/step-4.png" />
+    </Frame>
+  </Step>
+  <Step title="Proceed to Container Details">
+    Once done done with the **Deployment configuration**, proceed to **Container details**.
+  </Step>
+  <Step title="Set Image Path">
+    In the new container section, select **Existing container image**.
+
+
+    Copy the path to LLMstudio's image available on Docker Hub.
+    ```bash Image Path
+    tensoropsai/llmstudio:latest
+    ```
+    Set it as the **Image path** to your container.
+    <Frame>
+      <img src="how-to/deploy-on-gke/images/step-6.png" />
+    </Frame>
+  </Step>
+  <Step title="Set Environment Variables">
+    Configure the following mandatory environment variables:
+| Environment Variable       | Value     |
+|----------------------------|-----------|
+| `LLMSTUDIO_ENGINE_HOST`    | 0.0.0.0   |
+| `LLMSTUDIO_ENGINE_PORT`    | 8001      |
+| `LLMSTUDIO_TRACKING_HOST`  | 0.0.0.0   |
+| `LLMSTUDIO_TRACKING_PORT`  | 8002      |
+
+Additionally, set the `GOOGLE_API_KEY` environment variable to enable calls to Google's Gemini models.
+<Tip>Refer to **SDK/LLM/Providers** for instructions on setting up other providers.</Tip>
+
+<Frame>
+  <img src="how-to/deploy-on-gke/images/step-7.png" />
+</Frame>
+
+  </Step>
+  <Step title="Proceed to Expose (Optional)">
+    After configuring your container, proceed to **Expose (Optional)**.
+  </Step>
+  <Step title="Expose Ports">
+    Select **Expose deployment as a new service** and leave the first item as is.
+
+    <Frame>
+      <img src="how-to/deploy-on-gke/images/step-9-1.png" />
+    </Frame>
+
+    Add two other items, and expose the ports defined in the **Set Environment Variables** step.
+
+    <Frame>
+      <img src="how-to/deploy-on-gke/images/step-9-2.png" />
+    </Frame>
+  </Step>
+  <Step title="Deploy">
+    After setting up and exposing the ports, press **Deploy**.
+  <Check>You have successfully deployed **LLMstudio on Google Cloud Platform**!</Check>
+  </Step>
+
+</Steps>
+
+## Make a Call
+Now let's make a call to our LLMstudio instance on GCP!
+
+
+
+<Steps>
+  <Step title="Set Up Project">
+    Setup a simple project with this two files:
+    1. `calls.ipynb`
+    2. `.env`
+  </Step>
+
+  <Step title="Set Up Files">
+    <Tabs>
+      <Tab title=".env">
+
+        Go to your newly deployed **Workload**, scroll to the **Exposing services** section, and take note of the Host of your endpoint.
+        <Frame>
+          <img src="how-to/deploy-on-gke/images/step-env.png" />
+        </Frame>
+
+        Create your `.env` file with the following:
+
+        ```env .env
+        LLMSTUDIO_ENGINE_HOST = "YOUR_HOST"
+        LLMSTUDIO_ENGINE_PORT = "8001"
+        LLMSTUDIO_TRACKING_HOST = "YOUR_HOST"
+        LLMSTUDIO_TRACKING_PORT = "8002"
+        ```
+
+        <Check>You are done seting up you **.env** file!</Check>
+
+      </Tab>
+      <Tab title="calls.ipynb">
+        Start by importing llmstudio:
+        ```python 1st cell
+        from llmstudio import LLM
+        ```
+
+        Set up your LLM. We will be using `gemini-1.5-flash` for this guide.
+        ```python 2nd cell
+        llm = LLM('vertexai/gemini-1.5-flash')
+        ```
+
+        Chat with your model.
+        ```python 3rd cell
+        llm.chat('Hello!')
+        print(response.chat_output)
+        ```
+
+        <Frame>
+          <img src="how-to/deploy-on-gke/images/step-llmstudio-call.png" />
+        </Frame>
+
+
+        <Check>You are done calling llmstudio on GCP!</Check>
+
+      </Tab>
+
+    </Tabs>
+  </Step>
+
+
+</Steps>