blaxel 0.1.18rc61__tar.gz → 0.1.18rc62__tar.gz

blaxel-0.1.18rc62/PKG-INFO

@@ -0,0 +1,169 @@
+Metadata-Version: 2.4
+Name: blaxel
+Version: 0.1.18rc62
+Summary: Add your description here
+Project-URL: Homepage, https://blaxel.ai
+Project-URL: Documentation, https://docs.blaxel.ai
+Project-URL: Repository, https://github.com/blaxel-ai/sdk-python
+Project-URL: Changelog, https://docs.blaxel.ai/changelog
+Author-email: cploujoux <cploujoux@blaxel.ai>
+License-File: LICENSE
+Requires-Python: >=3.10
+Requires-Dist: attrs>=21.3.0
+Requires-Dist: httpx>=0.27.0
+Requires-Dist: mcp<=1.7.1
+Requires-Dist: opentelemetry-api>=1.28.0
+Requires-Dist: opentelemetry-exporter-otlp>=1.28.0
+Requires-Dist: opentelemetry-instrumentation-anthropic==0.40.6
+Requires-Dist: opentelemetry-instrumentation-cohere==0.40.6
+Requires-Dist: opentelemetry-instrumentation-fastapi==0.54b1
+Requires-Dist: opentelemetry-instrumentation-ollama==0.40.6
+Requires-Dist: opentelemetry-instrumentation-openai==0.40.6
+Requires-Dist: opentelemetry-instrumentation-system-metrics
+Requires-Dist: opentelemetry-sdk>=1.28.0
+Requires-Dist: pydantic<2.11.0,>=2.10.3
+Requires-Dist: pyjwt>=2.10.1
+Requires-Dist: python-dateutil>=2.8.0
+Requires-Dist: pyyaml<6.1.0,>=6.0.2
+Requires-Dist: requests<2.33.0,>=2.32.3
+Requires-Dist: tomli>=2.2.1
+Requires-Dist: websockets<15.0.0
+Provides-Extra: crewai
+Requires-Dist: crewai>=0.120.1; extra == 'crewai'
+Requires-Dist: opentelemetry-instrumentation-crewai>=0.40.6; extra == 'crewai'
+Provides-Extra: google-adk
+Requires-Dist: google-adk>=0.2.0; extra == 'google-adk'
+Requires-Dist: litellm>=1.63.11; extra == 'google-adk'
+Provides-Extra: langchain
+Requires-Dist: langchain-anthropic>=0.3.10; extra == 'langchain'
+Requires-Dist: langchain-cerebras>=0.5.0; extra == 'langchain'
+Requires-Dist: langchain-cohere>=0.4.3; extra == 'langchain'
+Requires-Dist: langchain-community<0.4.0,>=0.3.3; extra == 'langchain'
+Requires-Dist: langchain-core<0.4.0,>=0.3.13; extra == 'langchain'
+Requires-Dist: langchain-deepseek-official>=0.1.0.post1; extra == 'langchain'
+Requires-Dist: langchain-openai>=0.3.10; extra == 'langchain'
+Requires-Dist: langchain-xai>=0.2.2; extra == 'langchain'
+Requires-Dist: langgraph<0.3.0,>=0.2.40; extra == 'langchain'
+Requires-Dist: opentelemetry-instrumentation-langchain>=0.35.0; extra == 'langchain'
+Requires-Dist: pillow>=10.0.0; extra == 'langchain'
+Provides-Extra: livekit
+Requires-Dist: livekit-agents[anthropic,cartesia,deepgram,elevenlabs,groq,openai,silero,turn-detector]~=1.0; extra == 'livekit'
+Requires-Dist: livekit-plugins-noise-cancellation~=0.2; extra == 'livekit'
+Provides-Extra: llamaindex
+Requires-Dist: llama-index-llms-anthropic>=0.6.10; extra == 'llamaindex'
+Requires-Dist: llama-index-llms-cerebras>=0.2.2; extra == 'llamaindex'
+Requires-Dist: llama-index-llms-cohere>=0.4.0; extra == 'llamaindex'
+Requires-Dist: llama-index-llms-deepseek>=0.1.1; extra == 'llamaindex'
+Requires-Dist: llama-index-llms-google-genai>=0.1.7; extra == 'llamaindex'
+Requires-Dist: llama-index-llms-groq>=0.3.1; extra == 'llamaindex'
+Requires-Dist: llama-index-llms-mistralai>=0.4.0; extra == 'llamaindex'
+Requires-Dist: llama-index-llms-openai>=0.3.28; extra == 'llamaindex'
+Requires-Dist: llama-index>=0.12.26; extra == 'llamaindex'
+Requires-Dist: opentelemetry-instrumentation-llamaindex>=0.35.0; extra == 'llamaindex'
+Provides-Extra: openai-agents
+Requires-Dist: openai-agents>=0.0.7; extra == 'openai-agents'
+Provides-Extra: pydantic-ai
+Requires-Dist: pydantic-ai>=0.0.48; extra == 'pydantic-ai'
+Description-Content-Type: text/markdown
+
+# Blaxel Python SDK
+
+<p align="center">
+  <img src="https://blaxel.ai/logo-bg.png" alt="Blaxel"/>
+</p>
+
+**Blaxel is a computing platform for AI agent builders, with all the services and infrastructure to build and deploy agents efficiently.** This repository contains the Python SDK to create and manage resources on Blaxel.
+
+## Table of Contents
+
+- [Installation](#installation)
+  - [Authentication](#authentication)
+- [Features](#features)
+- [Quickstart](#quickstart)
+- [Contributing](#contributing)
+- [License](#license)
+
+
+
+## Installation
+
+Install Blaxel SDK which lets you manage Blaxel resources.
+
+```bash
+## Using pip
+pip install blaxel
+
+## Using uv
+uv pip install blaxel
+
+## Using uv add
+uv add blaxel
+``` 
+
+
+
+### Authentication
+
+The Blaxel SDK authenticates with your workspace using credentials from these sources, in priority order:
+1. When running on Blaxel, authentication is handled automatically
+2. Variables in your .env file (`BL_WORKSPACE` and `BL_API_KEY`, or see [this page](https://docs.blaxel.ai/Agents/Variables-and-secrets) for other authentication options).
+3. Environment variables from your machine
+4. Configuration file created locally when you log in through Blaxel CLI (or deploy on Blaxel)
+
+When developing locally, the recommended method is to just log in to your workspace with Blaxel CLI. This allows you to run Blaxel SDK functions that will automatically connect to your workspace without additional setup. When you deploy on Blaxel, this connection persists automatically.
+
+When running Blaxel SDK from a remote server that is not Blaxel-hosted, we recommend using environment variables as described in the third option above.
+
+
+
+## Features
+- Agents & MCP servers
+  - [Create MCP servers](https://docs.blaxel.ai/Functions/Create-MCP-server)
+  - [Connect to MCP servers and model APIs hosted on Blaxel](https://docs.blaxel.ai/Agents/Develop-an-agent-ts)
+  - [Call agents from another agent](https://docs.blaxel.ai/Agents/Develop-an-agent-ts#connect-to-another-agent-multi-agent-chaining)
+  - [Deploy on Blaxel](https://docs.blaxel.ai/Agents/Deploy-an-agent)
+- Sandboxes
+  - [Create and update sandboxes and sandbox previews](https://docs.blaxel.ai/Sandboxes/Overview)
+  - [Run filesystem operations and processes on a sandbox](https://docs.blaxel.ai/Sandboxes/Processes)
+- [Use environment variables or secrets](https://docs.blaxel.ai/Agents/Variables-and-secrets)
+
+
+
+## Quickstart
+
+Blaxel CLI gives you a quick way to create new applications: agents, MCP servers, jobs, etc - and deploy them to Blaxel.
+
+**Prerequisites**:
+- **Node.js:** v18 or later.
+- **Blaxel CLI:** Make sure you have Blaxel CLI installed. If not, [install it](https://docs.blaxel.ai/cli-reference/introduction):
+  ```bash
+  curl -fsSL \
+  https://raw.githubusercontent.com/blaxel-ai/toolkit/main/install.sh \
+  | BINDIR=/usr/local/bin sudo -E sh
+  ```
+- **Blaxel login:** Login to Blaxel:
+  ```bash
+    bl login YOUR-WORKSPACE
+  ```
+
+```bash
+bl create-agent-app myfolder
+cd myfolder
+bl deploy
+```
+
+Also available:
+-  `bl create-mcp-server`
+-  `bl create-job`
+
+
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+
+
+## License
+
+This project is licensed under the MIT License - see the LICENSE file for details.

blaxel-0.1.18rc62/README.md

@@ -0,0 +1,101 @@
+# Blaxel Python SDK
+
+<p align="center">
+  <img src="https://blaxel.ai/logo-bg.png" alt="Blaxel"/>
+</p>
+
+**Blaxel is a computing platform for AI agent builders, with all the services and infrastructure to build and deploy agents efficiently.** This repository contains the Python SDK to create and manage resources on Blaxel.
+
+## Table of Contents
+
+- [Installation](#installation)
+  - [Authentication](#authentication)
+- [Features](#features)
+- [Quickstart](#quickstart)
+- [Contributing](#contributing)
+- [License](#license)
+
+
+
+## Installation
+
+Install Blaxel SDK which lets you manage Blaxel resources.
+
+```bash
+## Using pip
+pip install blaxel
+
+## Using uv
+uv pip install blaxel
+
+## Using uv add
+uv add blaxel
+``` 
+
+
+
+### Authentication
+
+The Blaxel SDK authenticates with your workspace using credentials from these sources, in priority order:
+1. When running on Blaxel, authentication is handled automatically
+2. Variables in your .env file (`BL_WORKSPACE` and `BL_API_KEY`, or see [this page](https://docs.blaxel.ai/Agents/Variables-and-secrets) for other authentication options).
+3. Environment variables from your machine
+4. Configuration file created locally when you log in through Blaxel CLI (or deploy on Blaxel)
+
+When developing locally, the recommended method is to just log in to your workspace with Blaxel CLI. This allows you to run Blaxel SDK functions that will automatically connect to your workspace without additional setup. When you deploy on Blaxel, this connection persists automatically.
+
+When running Blaxel SDK from a remote server that is not Blaxel-hosted, we recommend using environment variables as described in the third option above.
+
+
+
+## Features
+- Agents & MCP servers
+  - [Create MCP servers](https://docs.blaxel.ai/Functions/Create-MCP-server)
+  - [Connect to MCP servers and model APIs hosted on Blaxel](https://docs.blaxel.ai/Agents/Develop-an-agent-ts)
+  - [Call agents from another agent](https://docs.blaxel.ai/Agents/Develop-an-agent-ts#connect-to-another-agent-multi-agent-chaining)
+  - [Deploy on Blaxel](https://docs.blaxel.ai/Agents/Deploy-an-agent)
+- Sandboxes
+  - [Create and update sandboxes and sandbox previews](https://docs.blaxel.ai/Sandboxes/Overview)
+  - [Run filesystem operations and processes on a sandbox](https://docs.blaxel.ai/Sandboxes/Processes)
+- [Use environment variables or secrets](https://docs.blaxel.ai/Agents/Variables-and-secrets)
+
+
+
+## Quickstart
+
+Blaxel CLI gives you a quick way to create new applications: agents, MCP servers, jobs, etc - and deploy them to Blaxel.
+
+**Prerequisites**:
+- **Node.js:** v18 or later.
+- **Blaxel CLI:** Make sure you have Blaxel CLI installed. If not, [install it](https://docs.blaxel.ai/cli-reference/introduction):
+  ```bash
+  curl -fsSL \
+  https://raw.githubusercontent.com/blaxel-ai/toolkit/main/install.sh \
+  | BINDIR=/usr/local/bin sudo -E sh
+  ```
+- **Blaxel login:** Login to Blaxel:
+  ```bash
+    bl login YOUR-WORKSPACE
+  ```
+
+```bash
+bl create-agent-app myfolder
+cd myfolder
+bl deploy
+```
+
+Also available:
+-  `bl create-mcp-server`
+-  `bl create-job`
+
+
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+
+
+## License
+
+This project is licensed under the MIT License - see the LICENSE file for details.

{blaxel-0.1.18rc61 → blaxel-0.1.18rc62}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "blaxel"
-version = "0.1.18.pre-61"
+version = "0.1.18.pre-62"
 description = "Add your description here"
 readme = "README.md"
 authors = [{ name = "cploujoux", email = "cploujoux@blaxel.ai" }]
@@ -92,3 +92,9 @@ ignore = ["UP006", "UP007", "UP035"]
 
 [tool.hatch.build.targets.wheel]
 packages = ["src/blaxel"]
+
+[project.urls]
+Homepage = "https://blaxel.ai"
+Documentation = "https://docs.blaxel.ai"
+Repository = "https://github.com/blaxel-ai/sdk-python"
+Changelog = "https://docs.blaxel.ai/changelog"

blaxel-0.1.18rc61/PKG-INFO

@@ -1,397 +0,0 @@
-Metadata-Version: 2.4
-Name: blaxel
-Version: 0.1.18rc61
-Summary: Add your description here
-Author-email: cploujoux <cploujoux@blaxel.ai>
-License-File: LICENSE
-Requires-Python: >=3.10
-Requires-Dist: attrs>=21.3.0
-Requires-Dist: httpx>=0.27.0
-Requires-Dist: mcp<=1.7.1
-Requires-Dist: opentelemetry-api>=1.28.0
-Requires-Dist: opentelemetry-exporter-otlp>=1.28.0
-Requires-Dist: opentelemetry-instrumentation-anthropic==0.40.6
-Requires-Dist: opentelemetry-instrumentation-cohere==0.40.6
-Requires-Dist: opentelemetry-instrumentation-fastapi==0.54b1
-Requires-Dist: opentelemetry-instrumentation-ollama==0.40.6
-Requires-Dist: opentelemetry-instrumentation-openai==0.40.6
-Requires-Dist: opentelemetry-instrumentation-system-metrics
-Requires-Dist: opentelemetry-sdk>=1.28.0
-Requires-Dist: pydantic<2.11.0,>=2.10.3
-Requires-Dist: pyjwt>=2.10.1
-Requires-Dist: python-dateutil>=2.8.0
-Requires-Dist: pyyaml<6.1.0,>=6.0.2
-Requires-Dist: requests<2.33.0,>=2.32.3
-Requires-Dist: tomli>=2.2.1
-Requires-Dist: websockets<15.0.0
-Provides-Extra: crewai
-Requires-Dist: crewai>=0.120.1; extra == 'crewai'
-Requires-Dist: opentelemetry-instrumentation-crewai>=0.40.6; extra == 'crewai'
-Provides-Extra: google-adk
-Requires-Dist: google-adk>=0.2.0; extra == 'google-adk'
-Requires-Dist: litellm>=1.63.11; extra == 'google-adk'
-Provides-Extra: langchain
-Requires-Dist: langchain-anthropic>=0.3.10; extra == 'langchain'
-Requires-Dist: langchain-cerebras>=0.5.0; extra == 'langchain'
-Requires-Dist: langchain-cohere>=0.4.3; extra == 'langchain'
-Requires-Dist: langchain-community<0.4.0,>=0.3.3; extra == 'langchain'
-Requires-Dist: langchain-core<0.4.0,>=0.3.13; extra == 'langchain'
-Requires-Dist: langchain-deepseek-official>=0.1.0.post1; extra == 'langchain'
-Requires-Dist: langchain-openai>=0.3.10; extra == 'langchain'
-Requires-Dist: langchain-xai>=0.2.2; extra == 'langchain'
-Requires-Dist: langgraph<0.3.0,>=0.2.40; extra == 'langchain'
-Requires-Dist: opentelemetry-instrumentation-langchain>=0.35.0; extra == 'langchain'
-Requires-Dist: pillow>=10.0.0; extra == 'langchain'
-Provides-Extra: livekit
-Requires-Dist: livekit-agents[anthropic,cartesia,deepgram,elevenlabs,groq,openai,silero,turn-detector]~=1.0; extra == 'livekit'
-Requires-Dist: livekit-plugins-noise-cancellation~=0.2; extra == 'livekit'
-Provides-Extra: llamaindex
-Requires-Dist: llama-index-llms-anthropic>=0.6.10; extra == 'llamaindex'
-Requires-Dist: llama-index-llms-cerebras>=0.2.2; extra == 'llamaindex'
-Requires-Dist: llama-index-llms-cohere>=0.4.0; extra == 'llamaindex'
-Requires-Dist: llama-index-llms-deepseek>=0.1.1; extra == 'llamaindex'
-Requires-Dist: llama-index-llms-google-genai>=0.1.7; extra == 'llamaindex'
-Requires-Dist: llama-index-llms-groq>=0.3.1; extra == 'llamaindex'
-Requires-Dist: llama-index-llms-mistralai>=0.4.0; extra == 'llamaindex'
-Requires-Dist: llama-index-llms-openai>=0.3.28; extra == 'llamaindex'
-Requires-Dist: llama-index>=0.12.26; extra == 'llamaindex'
-Requires-Dist: opentelemetry-instrumentation-llamaindex>=0.35.0; extra == 'llamaindex'
-Provides-Extra: openai-agents
-Requires-Dist: openai-agents>=0.0.7; extra == 'openai-agents'
-Provides-Extra: pydantic-ai
-Requires-Dist: pydantic-ai>=0.0.48; extra == 'pydantic-ai'
-Description-Content-Type: text/markdown
-
-# Blaxel Python SDK
-
-<p align="center">
-  <img src="https://blaxel.ai/logo.png" alt="Blaxel"/>
-</p>
-
-An SDK to connect your agent or tools with Blaxel platform.
-Currently in preview, feel free to send us feedback or contribute to the project.
-
-## Table of Contents
-
-- [Features](#features)
-- [Prerequisites](#prerequisites)
-- [Start from an hello world example](#start-from-an-hello-world-example)
-- [Integrate with a custom code](#integrate-with-a-custom-code)
-  - [Set-up blaxel observability](#set-up-blaxel-observability)
-  - [Connect tools and model from blaxel platform to your agent](#connect-tools-and-model-from-blaxel-platform-to-your-agent)
-  - [Agent Chaining](#agent-chaining)
-  - [Deploy on blaxel](#deploy-on-blaxel)
-  - [Advanced configuration](#advanced-configuration)
-  - [Create an MCP Server](#create-an-mcp-server)
-  - [Connect an existing MCP Server to blaxel](#connect-an-existing-mcp-server-to-blaxel)
-  - [How to use environment variables or secrets](#how-to-use-environment-variables-or-secrets)
-- [Contributing](#contributing)
-- [License](#license)
-
-## Features
-
-Supported AI frameworks:
-
-- LangChain
-- LlamaIndex
-- CrewAI
-- OpenAI Agents
-
-Supported Tools frameworks:
-
-- MCP (Model Context Protocol)
-
-## Prerequisites
-
-- **Python:** 3.10 or later
-- **Blaxel CLI:** Ensure you have the Blaxel CLI installed. If not, install it globally:
-  ```bash
-  curl -fsSL https://raw.githubusercontent.com/beamlit/toolkit/preview/install.sh | BINDIR=$HOME/.local/bin sh
-  ```
-- **Blaxel login:** Login to Blaxel platform
-  ```bash
-    bl login YOUR-WORKSPACE
-  ```
-
-## Start from an hello world example
-
-```bash
-bl create-agent-app myfolder
-cd myfolder
-bl serve --hotreload
-```
-
-## Integrate with a custom code
-
-### Set-up blaxel observability
-
-It only needs an import of our SDK on top of your main entrypoint file.
-It will directly plug our backend (when deployed on blaxel) with open telemetry standard.
-
-```python
-from blaxel import sdk
-```
-
-### Connect tools and model from blaxel platform to your agent
-
-```python
-from blaxel.models import bl_model
-from blaxel.tools import bl_tools
-```
-
-Then you need to use it in your agent. Here are examples with different frameworks:
-
-```python
-# Example with LangChain
-from langchain.agents import AgentExecutor, create_react_agent
-from langchain.prompts import ChatPromptTemplate
-from langchain.tools import Tool
-from langchain_core.messages import HumanMessage
-
-async def create_agent():
-    model = await bl_model("gpt-4o-mini").to_langchain()
-    async with bl_tools(["blaxel-search", "webcrawl"]) as t:
-        tools = t.to_langchain()
-        tools.append(
-            Tool(
-                name="weather",
-                description="Get the weather in a specific city",
-                func=lambda city: f"The weather in {city} is sunny"
-            )
-        )
-
-        prompt = ChatPromptTemplate.from_messages([
-            ("system", "You are a helpful assistant."),
-            ("human", "{input}")
-        ])
-
-        agent = create_react_agent(model, tools, prompt)
-        return AgentExecutor(agent=agent, tools=tools)
-
-# Example with LlamaIndex
-from llama_index.core import SimpleDirectoryReader
-from llama_index.core.agent import ReActAgent
-from llama_index.core.tools import FunctionTool
-
-async def create_llamaindex_agent():
-    model = await bl_model("gpt-4o-mini").to_llamaindex()
-    async with bl_tools(["blaxel-search", "webcrawl"]) as t:
-        tools = t.to_llamaindex()
-        tools.append(
-            FunctionTool.from_defaults(
-                fn=lambda city: f"The weather in {city} is sunny",
-                name="weather",
-                description="Get the weather in a specific city"
-            )
-        )
-
-        return ReActAgent.from_tools(
-            tools,
-            llm=model,
-            verbose=True
-        )
-
-# Example with CrewAI
-from crewai import Agent, Task, Crew
-
-async def create_crewai_agent():
-    model = await bl_model("gpt-4o-mini").to_crewai()
-    async with bl_tools(["blaxel-search", "webcrawl"]) as t:
-        tools = t.to_crewai()
-        tools.append(
-            Tool(
-                name="weather",
-                description="Get the weather in a specific city",
-                func=lambda city: f"The weather in {city} is sunny"
-            )
-        )
-
-        agent = Agent(
-            role='Assistant',
-            goal='Help users with their queries',
-            backstory='I am a helpful AI assistant',
-            tools=tools,
-            llm=model
-        )
-
-        return agent
-```
-
-### Agent Chaining
-
-You can call an agent from another agent to chain them.
-This allows complex agentic logic, with multiple agents calling each other, orchestration, routing, etc.
-
-```python
-# Example of calling an agent, then putting its result inside a second one
-from blaxel.agents import bl_agent
-
-async def first_agent(input_text: str) -> dict:
-    # First agent that processes loan applications
-    response = await bl_agent("first-agent").run({
-        "inputs": input_text
-    })
-    return response
-
-async def second_agent(input_text: str) -> dict:
-    # Second agent that evaluates the loan application
-    first_response = await first_agent(input_text)
-
-    model = await bl_model("gpt-4o-mini").to_langchain()
-    prompt = ChatPromptTemplate.from_messages([
-        ("system", "You are a loan specialist. Based on the given json file with client data, your job is to decide if a client can be further processed."),
-        ("human", "{input}")
-    ])
-
-    response = await model.ainvoke(first_response)
-    return response
-```
-
-### Deploy on blaxel
-
-To deploy on blaxel, we have only one requirement in each agent code.
-We need an HTTP Server.
-
-For example with FastAPI:
-
-```python
-from fastapi import FastAPI
-from blaxel import sdk
-import uvicorn
-
-app = FastAPI()
-
-@app.post("/")
-async def root(inputs: str):
-    # Your agentic logic here
-    return {"response": "Your response here"}
-
-if __name__ == "__main__":
-    port = int(os.getenv("BL_SERVER_PORT", "3000"))
-    host = os.getenv("BL_SERVER_HOST", "0.0.0.0")
-    uvicorn.run(app, host=host, port=port)
-```
-
-```bash
-bl deploy
-```
-
-### Advanced configuration
-
-You can add optionally a configuration file "blaxel.toml" in your project root.
-
-```toml
-name = "my-agent"
-workspace = "my-workspace"
-type = "agent"
-
-functions = ["blaxel-search"]
-models = ["sandbox-openai"]
-```
-
-It allows to customize the requirements for your agent, it can be useful if you have many models and functions in your workspace.
-
-### Create an MCP Server
-
-If you want to create an MCP Server for using it in multiple agents, you can bootstrap it with the following command:
-
-```bash
-bl create-mcp-server my-mcp-server
-cd my-mcp-server
-bl serve --hotreload
-```
-
-We follow current standard for tool development over MCP Server.
-Example of a tool which is sending fake information about the weather:
-
-```python
-from blaxel.mcp.server import FastMCP
-
-mcp = FastMCP("My Weather MCP server")
-
-@mcp.tool()
-def weather(city: str) -> str:
-    """Get the weather for a city"""
-    return f"The weather in {city} is sunny"
-
-if __name__ == "__main__":
-    if os.getenv("BL_SERVER_PORT"):
-      mcp.run(transport="ws")
-    else:
-      mcp.run(transport="stdio")
-
-
-```
-
-### Connect an existing MCP Server to blaxel
-
-You need to have a "blaxel.toml" file in your project root:
-
-```toml
-name = "weather"
-workspace = "my-workspace"
-type = "function"
-```
-
-Connect the observability layer:
-
-```python
-from blaxel import sdk
-```
-
-Update your import of FastMCP
-
-```python
-from blaxel.mcp.server import FastMCP
-```
-
-Update your entrypoint to support our transport:
-
-```python
-def main():
-    mcp.run(transport="ws") if os.getenv("BL_SERVER_PORT") else mcp.run(transport="stdio")
-```
-
-### How to use environment variables or secrets
-
-You can use the "blaxel.toml" config file to specify environment variables for your agent:
-
-```toml
-name = "weather"
-workspace = "my-workspace"
-type = "function"
-
-[env]
-DEFAULT_CITY = "San Francisco"
-```
-
-Then you can use it in your agent or function with the following syntax:
-
-```python
-from blaxel.env import env
-print(env.DEFAULT_CITY)  # San Francisco
-```
-
-You can also add secrets variables to a .env files in your project root. (goal is to not commit this file)
-
-Example of a .env file:
-
-```
-# Secret variables can be stored here
-DEFAULT_CITY_PASSWORD=123456
-```
-
-Then you can use it in your agent or function with the following syntax:
-
-```python
-from blaxel.env import env
-print(env.DEFAULT_CITY_PASSWORD)  # 123456
-```
-
-## Contributing
-
-Contributions are welcome! Please feel free to submit a Pull Request.
-
-## License
-
-This project is licensed under the MIT License - see the LICENSE file for details.