Integrations集成方案
oBeaver exposes an OpenAI-compatible API, so it works seamlessly with any framework that supports the OpenAI protocol. Just change the base_url to your local server.oBeaver 提供 OpenAI 兼容 API，可与任何支持 OpenAI 协议的框架无缝配合。只需将 base_url 指向本地服务器。
OpenAI Python SDK
python
from openai import OpenAI
client = OpenAI(base_url="http://127.0.0.1:18000/v1", api_key="unused")
response = client.chat.completions.create(
model="Phi-4-mini",
messages=[{"role": "user", "content": "What is the capital of France?"}],
stream=True,
)
for chunk in response:
print(chunk.choices[0].delta.content or "", end="", flush=True)Tip: Point any OpenAI-compatible framework (LangChain, LlamaIndex, Microsoft Agent Framework, CrewAI, etc.) at http://127.0.0.1:18000/v1 and it just works. The api_key can be any non-empty string.提示：将任何 OpenAI 兼容框架（LangChain、LlamaIndex、Microsoft Agent Framework、CrewAI 等）指向 http://127.0.0.1:18000/v1 即可使用。api_key 可以是任意非空字符串。
Compatible Frameworks兼容框架
Any framework that supports the OpenAI API protocol works with oBeaver:任何支持 OpenAI API 协议的框架都可与 oBeaver 配合使用：
| Framework | Type | Notes |
|---|---|---|
| OpenAI Python SDK | Base SDK | Direct support. Change base_url only. |
| LangChain | Orchestration | Via ChatOpenAI with custom base_url |
| LlamaIndex | RAG Framework | Via OpenAILike with custom api_base |
| Microsoft Agent Framework | Agentic AI | Full tool-calling support |
| CrewAI | Multi-agent | Via OpenAI-compatible endpoint |