Skip to content

W-23612601 Rename LLM Proxy to Model Proxy #701

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

Open
glenn-rodgers-sf wants to merge 1 commit into
base: latest
Choose a base branch
from
+8 −8
Open

W-23612601 Rename LLM Proxy to Model Proxy #701

Show file tree
Hide file tree
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
6 changes: 3 additions & 3 deletions agent-network/1.0/modules/ROOT/pages/af-agent-networks.adoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -131,7 +131,7 @@ NOTE: In a shared space, or in a private space using a single-gateway configurat
[[llm-support]]
== Large Language Models

Agent network brokers support the latest Gemini and OpenAI models and LLM Proxies.
Agent network brokers support the latest Gemini and OpenAI models and Model Proxies.

* Azure OpenAI and OpenAI API:
+
Expand All @@ -152,9 +152,9 @@ For more information about these models, see the https://developers.openai.com/a
+
For more information about these models, see the https://ai.google.dev/gemini-api/docs/models[Gemini] documentation.

* LLM Proxy:
* Model Proxy:
+
LLM Proxy provides a unified endpoint for multiple LLM providers including Gemini, OpenAI, Bedrock (Anthropic Claude models), and NVIDIA Nemotron. To find the supported models, see xref:gateway::flex-gateway-llm-proxy.adoc#supported-llm-providers[LLM Proxy Supported LLM Providers].
Model Proxy provides a unified endpoint for multiple LLM providers including Gemini, OpenAI, Bedrock (Anthropic Claude models), and NVIDIA Nemotron. To find the supported models, see xref:general::model-proxy.adoc#supported-llm-providers[Model Proxy Supported LLM Providers].

This table details the requirements and recommended models.

Expand Down
4 changes: 2 additions & 2 deletions agent-network/1.0/modules/ROOT/pages/af-project-files.adoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -230,7 +230,7 @@ The `spec` element has these properties.

`llm`

The value of this section is a reference to one of the LLMs defined in Anypoint Exchange or in the `llmProviders` section of `agent-network.yaml`. Because it's a reference, you can choose to share the same LLM across all the brokers in your agent network. Or, you can have different brokers use different LLMs to better suit their tasks. If using an LLM Proxy, configure the LLM Proxy as either an OpenAI or Gemini LLM depending on the proxy's format.
The value of this section is a reference to one of the LLMs defined in Anypoint Exchange or in the `llmProviders` section of `agent-network.yaml`. Because it's a reference, you can choose to share the same LLM across all the brokers in your agent network. Or, you can have different brokers use different LLMs to better suit their tasks. If using a Model Proxy, configure the Model Proxy as either an OpenAI or Gemini LLM depending on the proxy's format.

For more information about supported LLMs, see xref:af-agent-networks.adoc#llm-support[Large Language Models].

Expand Down Expand Up @@ -745,7 +745,7 @@ connections:
spec:
url: https://api.openai.com/v1/
configuration:
apiKey: ${openai.apiKey} # Define the API key of an LLM Proxy as <<clientId>>:<<clientSecret>>
apiKey: ${openai.apiKey} # Define the API key of a Model Proxy as <<clientId>>:<<clientSecret>>

talent-pool-mcp:
kind: mcp
Expand Down
6 changes: 3 additions & 3 deletions agent-network/2.0/modules/ROOT/pages/af-agent-networks.adoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -142,7 +142,7 @@ Applications or APIs exposed through the Model Context Protocol (MCP). MCP is an
[[llm-support]]
== Large Language Models

Agent network brokers support the latest models from OpenAI, Azure OpenAI, Bedrock OpenAI, and Gemini, as well as LLM Proxies.
Agent network brokers support the latest models from OpenAI, Azure OpenAI, Bedrock OpenAI, and Gemini, as well as Model Proxies.

* https://developers.openai.com/api/docs/models[OpenAI]
* https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models[Azure OpenAI]
Expand All @@ -151,9 +151,9 @@ Agent network brokers support the latest models from OpenAI, Azure OpenAI, Bedro
NOTE: Bedrock OpenAI uses the `openai.` prefix for model names (for example, `openai.gpt-5.5`), which differs from the model names used with OpenAI and Azure OpenAI.
* https://ai.google.dev/gemini-api/docs/models[Gemini]

* LLM Proxy
* Model Proxy
+
Agent network brokers only support access to OpenAI and Gemini through xref:gateway::flex-gateway-llm-proxy.adoc[Omni Gateway LLM Proxy]. Transcoding other models to OpenAI format to use in agent networks is not supported.
Agent network brokers only support access to OpenAI and Gemini through xref:general::model-proxy.adoc[Omni Gateway Model Proxy]. Transcoding other models to OpenAI format to use in agent networks is not supported.

This table details requirements and recommended models.

Expand Down