Skip to content

docs: add governed OpenAI-compatible endpoint example #11514

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
cerebrixos wants to merge 1 commit into from
+15 −0
Closed

docs: add governed OpenAI-compatible endpoint example #11514

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 15 additions & 0 deletions docs-website/docs/pipeline-components/generators/openaichatgenerator.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,21 @@ You can pass any chat completion parameters valid for the `openai.ChatCompletion

`OpenAIChatGenerator` can support custom deployments of your OpenAI models through the `api_base_url` init parameter.

You can also use `api_base_url` with a governed OpenAI-compatible endpoint when you want Haystack to keep owning pipeline orchestration, retrieval, and component composition while a centralized control plane handles model access, policy, audit trails, quotas, routing, and cost reporting. For example, [Tuning Engines](https://www.tuningengines.com/) exposes an OpenAI-compatible inference endpoint:

```python
import os

from haystack.components.generators.chat import OpenAIChatGenerator
from haystack.utils import Secret

llm = OpenAIChatGenerator(
model=os.environ.get("TUNING_ENGINES_MODEL", "your-model-alias"),
api_base_url="https://api.tuningengines.com/v1",
api_key=Secret.from_env_var("TUNING_ENGINES_API_KEY"),
)
```

### Structured Output

`OpenAIChatGenerator` supports structured output generation, allowing you to receive responses in a predictable format. You can use Pydantic models or JSON schemas to define the structure of the output through the `response_format` parameter in `generation_kwargs`.
Expand Down