Skip to content

docs: OpenAI-compatible multi-model gateway example (DaoXE) #561

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
seven7763 wants to merge 1 commit into from
+29 −0
Closed

docs: OpenAI-compatible multi-model gateway example (DaoXE) #561

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
29 changes: 29 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -158,6 +158,35 @@ text = (
)
asyncio.run(kg_builder.run_async(text=text))
driver.close()

### OpenAI-compatible multi-model gateways

@ali-sedaghatbaf ali-sedaghatbaf Jul 16, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

With your change, the README would promote a specific third-party service (DaoXE) with a direct URL. This is unusual for an open-source library README. A more neutral approach would use a generic placeholder like https://your-gateway.example.com/v1 and mention well-known alternatives (LiteLLM, vLLM, Ollama, Azure OpenAI, etc.) rather than one lesser-known commercial gateway.


`OpenAILLM` and `OpenAIEmbeddings` accept OpenAI Python client kwargs such as `base_url` and `api_key`. Point them at any OpenAI-compatible Chat Completions / embeddings host. Example with [DaoXE](https://daoxe.com) (`https://daoxe.com/v1`):

```python
from neo4j_graphrag.embeddings import OpenAIEmbeddings
from neo4j_graphrag.llm import OpenAILLM

llm = OpenAILLM(
model_name="your-account-model-id", # exact ID from GET /v1/models or dashboard
api_key="your_daoxe_api_key",
base_url="https://daoxe.com/v1",
)

embedder = OpenAIEmbeddings(
model="your-account-embedding-model-id",
api_key="your_daoxe_api_key",
base_url="https://daoxe.com/v1",
)
```

Notes:

- Model IDs are account-scoped; do not hardcode a static public catalog.
- Chat Completions / embeddings paths only for this snippet.
- DaoXE is not available in mainland China.

@ali-sedaghatbaf ali-sedaghatbaf Jul 16, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is a product-specific limitation note that has no place in generic library doc

- Contributor disclosure: this example was contributed by a DaoXE affiliate.

@ali-sedaghatbaf ali-sedaghatbaf Jul 16, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This reads as an advertisement. It's atypical for library documentation to include affiliate disclosures inline


```

> Warning: In order to run this code, the `openai` Python package needs to be installed: `pip install "neo4j_graphrag[openai]"`
Expand Down
Loading