Skip to content

πŸ™Œ OpenHands: AI-Driven Development

Update MCP docs and LLM docs with more accurate information (#8482)

mamoodi1abed30b44af
diff --git a/docs/modules/usage/llms/azure-llms.md b/docs/modules/usage/llms/azure-llms.md
index a7b10a6084..8f6f501d6b 100644
--- a/docs/modules/usage/llms/azure-llms.md
+++ b/docs/modules/usage/llms/azure-llms.md
@@ -1,6 +1,7 @@
# Azure
-OpenHands uses LiteLLM to make calls to Azure's chat models. You can find their documentation on using Azure as a provider [here](https://docs.litellm.ai/docs/providers/azure).
+OpenHands uses LiteLLM to make calls to Azure's chat models. You can find their documentation on using Azure as a
+provider [here](https://docs.litellm.ai/docs/providers/azure).
## Azure OpenAI Configuration
@@ -18,7 +19,7 @@ docker run -it --pull=always \
...
```
-Then in the OpenHands UI Settings:
+Then in the OpenHands UI Settings under the `LLM` tab:
:::note
You will need your ChatGPT deployment name which can be found on the deployments page in Azure. This is referenced as
diff --git a/docs/modules/usage/llms/google-llms.md b/docs/modules/usage/llms/google-llms.md
index 4122de4bbe..ee0b6fab0e 100644
--- a/docs/modules/usage/llms/google-llms.md
+++ b/docs/modules/usage/llms/google-llms.md
@@ -7,10 +7,11 @@ OpenHands uses LiteLLM to make calls to Google's chat models. You can find their
## Gemini - Google AI Studio Configs
-When running OpenHands, you'll need to set the following in the OpenHands UI through the Settings:
+When running OpenHands, you'll need to set the following in the OpenHands UI through the Settings under the `LLM` tab:
- `LLM Provider` to `Gemini`
- `LLM Model` to the model you will be using.
-If the model is not in the list, toggle `Advanced` options, and enter it in `Custom Model` (e.g. gemini/<model-name> like `gemini/gemini-2.0-flash`).
+If the model is not in the list, enable `Advanced` options, and enter it in `Custom Model`
+(e.g. gemini/<model-name> like `gemini/gemini-2.0-flash`).
- `API Key` to your Gemini API key
## VertexAI - Google Cloud Platform Configs
@@ -24,7 +25,8 @@ VERTEXAI_PROJECT="<your-gcp-project-id>"
VERTEXAI_LOCATION="<your-gcp-location>"
```
-Then set the following in the OpenHands UI through the Settings:
+Then set the following in the OpenHands UI through the Settings under the `LLM` tab:
- `LLM Provider` to `VertexAI`
- `LLM Model` to the model you will be using.
-If the model is not in the list, toggle `Advanced` options, and enter it in `Custom Model` (e.g. vertex_ai/&lt;model-name&gt;).
+If the model is not in the list, enable `Advanced` options, and enter it in `Custom Model`
+(e.g. vertex_ai/&lt;model-name&gt;).
diff --git a/docs/modules/usage/llms/groq.md b/docs/modules/usage/llms/groq.md
index 0de104cf14..5c13a18f20 100644
--- a/docs/modules/usage/llms/groq.md
+++ b/docs/modules/usage/llms/groq.md
@@ -1,22 +1,21 @@
# Groq
-OpenHands uses LiteLLM to make calls to chat models on Groq. You can find their documentation on using Groq as a provider [here](https://docs.litellm.ai/docs/providers/groq).
+OpenHands uses LiteLLM to make calls to chat models on Groq. You can find their documentation on using Groq as a
+provider [here](https://docs.litellm.ai/docs/providers/groq).
## Configuration
-When running OpenHands, you'll need to set the following in the OpenHands UI through the Settings:
+When running OpenHands, you'll need to set the following in the OpenHands UI through the Settings under the `LLM` tab:
- `LLM Provider` to `Groq`
- `LLM Model` to the model you will be using. [Visit here to see the list of
-models that Groq hosts](https://console.groq.com/docs/models). If the model is not in the list, toggle
-`Advanced` options, and enter it in `Custom Model` (e.g. groq/&lt;model-name&gt; like `groq/llama3-70b-8192`).
+models that Groq hosts](https://console.groq.com/docs/models). If the model is not in the list,
+enable `Advanced` options, and enter it in `Custom Model` (e.g. groq/&lt;model-name&gt; like `groq/llama3-70b-8192`).
- `API key` to your Groq API key. To find or create your Groq API Key, [see here](https://console.groq.com/keys).
-
-
## Using Groq as an OpenAI-Compatible Endpoint
The Groq endpoint for chat completion is [mostly OpenAI-compatible](https://console.groq.com/docs/openai). Therefore, you can access Groq models as you
-would access any OpenAI-compatible endpoint. In the OpenHands UI through the Settings:
+would access any OpenAI-compatible endpoint. In the OpenHands UI through the Settings under the `LLM` tab:
1. Enable `Advanced` options
2. Set the following:
- `Custom Model` to the prefix `openai/` + the model you will be using (e.g. `openai/llama3-70b-8192`)
diff --git a/docs/modules/usage/llms/litellm-proxy.md b/docs/modules/usage/llms/litellm-proxy.md
index 21413e0ef1..7954b93714 100644
--- a/docs/modules/usage/llms/litellm-proxy.md
+++ b/docs/modules/usage/llms/litellm-proxy.md
@@ -7,7 +7,7 @@ OpenHands supports using the [LiteLLM proxy](https://docs.litellm.ai/docs/proxy/
To use LiteLLM proxy with OpenHands, you need to:
1. Set up a LiteLLM proxy server (see [LiteLLM documentation](https://docs.litellm.ai/docs/proxy/quick_start))
-2. When running OpenHands, you'll need to set the following in the OpenHands UI through the Settings:
+2. When running OpenHands, you'll need to set the following in the OpenHands UI through the Settings under the `LLM` tab:
* Enable `Advanced` options
* `Custom Model` to the prefix `litellm_proxy/` + the model you will be using (e.g. `litellm_proxy/anthropic.claude-3-5-sonnet-20241022-v2:0`)
* `Base URL` to your LiteLLM proxy URL (e.g. `https://your-litellm-proxy.com`)
@@ -15,6 +15,7 @@ To use LiteLLM proxy with OpenHands, you need to:
## Supported Models
-The supported models depend on your LiteLLM proxy configuration. OpenHands supports any model that your LiteLLM proxy is configured to handle.
+The supported models depend on your LiteLLM proxy configuration. OpenHands supports any model that your LiteLLM proxy
+is configured to handle.
Refer to your LiteLLM proxy configuration for the list of available models and their names.
diff --git a/docs/modules/usage/llms/local-llms.md b/docs/modules/usage/llms/local-llms.md
index 0cb01751a6..d7d4fca415 100644
--- a/docs/modules/usage/llms/local-llms.md
+++ b/docs/modules/usage/llms/local-llms.md
@@ -75,7 +75,7 @@ Start OpenHands using `make run`.
### Configure OpenHands
-Once OpenHands is running, you'll need to set the following in the OpenHands UI through the Settings:
+Once OpenHands is running, you'll need to set the following in the OpenHands UI through the Settings under the `LLM` tab:
1. Enable `Advanced` options.
2. Set the following:
- `Custom Model` to `openai/<served-model-name>` (e.g. `openai/openhands-lm-32b-v0.1`)
diff --git a/docs/modules/usage/llms/openai-llms.md b/docs/modules/usage/llms/openai-llms.md
index d035898969..3224af5210 100644
--- a/docs/modules/usage/llms/openai-llms.md
+++ b/docs/modules/usage/llms/openai-llms.md
@@ -1,14 +1,15 @@
# OpenAI
-OpenHands uses LiteLLM to make calls to OpenAI's chat models. You can find their documentation on using OpenAI as a provider [here](https://docs.litellm.ai/docs/providers/openai).
+OpenHands uses LiteLLM to make calls to OpenAI's chat models. You can find their documentation on using OpenAI as a
+provider [here](https://docs.litellm.ai/docs/providers/openai).
## Configuration
-When running OpenHands, you'll need to set the following in the OpenHands UI through the Settings:
+When running OpenHands, you'll need to set the following in the OpenHands UI through the Settings under the `LLM` tab:
* `LLM Provider` to `OpenAI`
* `LLM Model` to the model you will be using.
[Visit here to see a full list of OpenAI models that LiteLLM supports.](https://docs.litellm.ai/docs/providers/openai#openai-chat-completion-models)
-If the model is not in the list, toggle `Advanced` options, and enter it in `Custom Model` (e.g. openai/&lt;model-name&gt; like `openai/gpt-4o`).
+If the model is not in the list, enable `Advanced` options, and enter it in `Custom Model` (e.g. openai/&lt;model-name&gt; like `openai/gpt-4o`).
* `API Key` to your OpenAI API key. To find or create your OpenAI Project API Key, [see here](https://platform.openai.com/api-keys).
## Using OpenAI-Compatible Endpoints
@@ -17,7 +18,7 @@ Just as for OpenAI Chat completions, we use LiteLLM for OpenAI-compatible endpoi
## Using an OpenAI Proxy
-If you're using an OpenAI proxy, in the OpenHands UI through the Settings:
+If you're using an OpenAI proxy, in the OpenHands UI through the Settings under the `LLM` tab:
1. Enable `Advanced` options
2. Set the following:
- `Custom Model` to openai/&lt;model-name&gt; (e.g. `openai/gpt-4o` or openai/&lt;proxy-prefix&gt;/&lt;model-name&gt;)
diff --git a/docs/modules/usage/llms/openrouter.md b/docs/modules/usage/llms/openrouter.md
index 2b5204d26c..0895b31fe3 100644
--- a/docs/modules/usage/llms/openrouter.md
+++ b/docs/modules/usage/llms/openrouter.md
@@ -1,12 +1,14 @@
# OpenRouter
-OpenHands uses LiteLLM to make calls to chat models on OpenRouter. You can find their documentation on using OpenRouter as a provider [here](https://docs.litellm.ai/docs/providers/openrouter).
+OpenHands uses LiteLLM to make calls to chat models on OpenRouter. You can find their documentation on using
+OpenRouter as a provider [here](https://docs.litellm.ai/docs/providers/openrouter).
## Configuration
-When running OpenHands, you'll need to set the following in the OpenHands UI through the Settings:
+When running OpenHands, you'll need to set the following in the OpenHands UI through the Settings under the `LLM` tab:
* `LLM Provider` to `OpenRouter`
* `LLM Model` to the model you will be using.
[Visit here to see a full list of OpenRouter models](https://openrouter.ai/models).
-If the model is not in the list, toggle `Advanced` options, and enter it in `Custom Model` (e.g. openrouter/&lt;model-name&gt; like `openrouter/anthropic/claude-3.5-sonnet`).
+If the model is not in the list, enable `Advanced` options, and enter it in
+`Custom Model` (e.g. openrouter/&lt;model-name&gt; like `openrouter/anthropic/claude-3.5-sonnet`).
* `API Key` to your OpenRouter API key.
diff --git a/docs/modules/usage/mcp.md b/docs/modules/usage/mcp.md
index a91fe34015..50742362b5 100644
--- a/docs/modules/usage/mcp.md
+++ b/docs/modules/usage/mcp.md
@@ -13,9 +13,11 @@ or custom tools. MCP is based on the open standard defined at [modelcontextproto
## Configuration
-MCP configuration is defined in the `[mcp]` section of your `config.toml` file.
+MCP configuration can be defined in:
+* The OpenHands UI through the Settings under the `MCP` tab.
+* The `config.toml` file under the `[mcp]` section if not using the UI.
-### Configuration Example
+### Configuration Example via config.toml
```toml
[mcp]
@@ -82,7 +84,7 @@ Stdio servers are configured using an object with the following properties:
When OpenHands starts, it:
-1. Reads the MCP configuration from `config.toml`.
+1. Reads the MCP configuration.
2. Connects to any configured SSE servers.
3. Starts any configured stdio servers.
4. Registers the tools provided by these servers with the agent.