Compatible (BYOK)

Use LlamaIndex with GlideflowAI.

A data-focused framework with an OpenAI-like client for compatible LLM APIs. Connect it through GlideflowAI's OpenAI-compatible API with a key you control.

Get a key

What this connection is for

LlamaIndex is a data-focused framework for applications that ingest, retrieve, index, and reason over their own information. It is for developers building a knowledge-backed feature where the language model is only one part of a larger document or retrieval pipeline. Its provider layer can stay replaceable while indexes, retrieval settings, and application-specific data flows remain under the developer's control.

Choose LlamaIndex when retrieval quality, document handling, and data connectors matter as much as the final model call. It is not the shortest route for a simple chat completion or a one-off command-line test. When testing a new compatible endpoint, evaluate it against representative retrieved context, because an empty prompt does not reveal how a model handles your actual source material.

LlamaIndex provides an OpenAILike wrapper for third-party compatible APIs. Set api_base to GlideflowAI's /v1 endpoint, load the key from the runtime environment, and assign an exact model ID to the LLM used by your query pipeline. Keep retrieval settings fixed during the first provider comparison so model changes remain the variable being tested. LlamaIndex is an independent project; this is a user-managed connection, not an endorsement or partnership.

Why pair it with GlideflowAI

LlamaIndex's OpenAILike wrapper makes the gateway a replaceable LLM component inside a retrieval pipeline rather than a special-case integration.

That makes it easier to compare model behavior on the same retrieved documents while keeping index and connector code unchanged.

Setup

Use a new API key for the tool, select a model from the catalog, and begin with a small task. Do not put a key in a repository, screenshot, or shared configuration file.

1
Set a private application key
Provide the key through the runtime environment rather than an indexed document store or source file.
```
export GLIDEFLOW_API_KEY="sk-your-key"
```

Use the OpenAILike wrapper

Create the LLM with the compatible API base and the exact model ID you want to call.

from llama_index.llms.openai_like import OpenAILike

llm = OpenAILike(
    model="glm-5.2",
    api_base="https://api.glideflowai.com/v1",
    api_key=os.environ["GLIDEFLOW_API_KEY"],
)

Need the endpoint basics? Read authentication, browse the model catalog, or compare pricing.

Frequently asked questions

Which LlamaIndex class supports GlideflowAI?

Use OpenAILike and supply api_base=https://api.glideflowai.com/v1 plus the gateway API key and exact model ID.

Should I evaluate only a direct prompt?

No. Test with representative retrieved chunks, because context length, citations, and source formatting can affect the result of a real query pipeline.

Where should the key be stored in a LlamaIndex app?

Read it from your service environment or secret manager, not from indexed documents, notebooks shared with collaborators, or repository configuration.

Is this an official integration?

No. The connection is configured by you using a compatible API and does not imply sponsorship, endorsement, or a partnership.

Ready to connect LlamaIndex?

Create a key, use the setup above, and verify the connection on a small task before you scale it up.