diff --git a/docs/api/anthropic-compatibility.mdx b/docs/api/anthropic-compatibility.mdx index f12a0beb1..81ec04d47 100644 --- a/docs/api/anthropic-compatibility.mdx +++ b/docs/api/anthropic-compatibility.mdx @@ -4,16 +4,6 @@ title: Anthropic compatibility Ollama provides compatibility with the [Anthropic Messages API](https://docs.anthropic.com/en/api/messages) to help connect existing applications to Ollama, including tools like Claude Code. -## Recommended models - -For coding use cases, models like `glm-4.7:cloud`, `minimax-m2.1:cloud`, and `qwen3-coder` are recommended. - -Pull a model before use: -```shell -ollama pull qwen3-coder -ollama pull glm-4.7:cloud -``` - ## Usage ### Environment variables @@ -22,8 +12,8 @@ To use Ollama with tools that expect the Anthropic API (like Claude Code), set t ```shell export ANTHROPIC_AUTH_TOKEN=ollama # required but ignored +export ANTHROPIC_API_KEY="" # required but ignored export ANTHROPIC_BASE_URL=http://localhost:11434 -export ANTHROPIC_API_KEY=ollama # required but ignored ``` ### Simple `/v1/messages` example @@ -245,10 +235,41 @@ curl -X POST http://localhost:11434/v1/messages \ ## Using with Claude Code -[Claude Code](https://code.claude.com/docs/en/overview) can be configured to use Ollama as its backend: +[Claude Code](https://code.claude.com/docs/en/overview) can be configured to use Ollama as its backend. + +### Recommended models + +For coding use cases, models like `glm-4.7`, `minimax-m2.1`, and `qwen3-coder` are recommended. + +Download a model before use: ```shell -ANTHROPIC_AUTH_TOKEN=ollama ANTHROPIC_BASE_URL=http://localhost:11434 ANTHROPIC_API_KEY=ollama claude --model qwen3-coder +ollama pull qwen3-coder +``` +> Note: Qwen 3 coder is a 30B parameter model requiring at least 24GB of VRAM to run smoothly. More is required for longer context lengths. + +```shell +ollama pull glm-4.7:cloud +``` + +### Quick setup + +```shell +ollama launch claude +``` + +This will prompt you to select a model, configure Claude Code automatically, and launch it. To configure without launching: + +```shell +ollama launch claude --config +``` + +### Manual setup + +Set the environment variables and run Claude Code: + +```shell +ANTHROPIC_AUTH_TOKEN=ollama ANTHROPIC_BASE_URL=http://localhost:11434 ANTHROPIC_API_KEY="" claude --model qwen3-coder ``` Or set the environment variables in your shell profile: @@ -256,19 +277,13 @@ Or set the environment variables in your shell profile: ```shell export ANTHROPIC_AUTH_TOKEN=ollama export ANTHROPIC_BASE_URL=http://localhost:11434 -export ANTHROPIC_API_KEY=ollama +export ANTHROPIC_API_KEY="" ``` Then run Claude Code with any Ollama model: ```shell -# Local models claude --model qwen3-coder -claude --model gpt-oss:20b - -# Cloud models -claude --model glm-4.7:cloud -claude --model minimax-m2.1:cloud ``` ## Endpoints diff --git a/docs/cli.mdx b/docs/cli.mdx index 97810e64a..ecceee41d 100644 --- a/docs/cli.mdx +++ b/docs/cli.mdx @@ -8,6 +8,47 @@ title: CLI Reference ollama run gemma3 ``` +### Launch integrations + +``` +ollama launch +``` + +Configure and launch external applications to use Ollama models. This provides an interactive way to set up and start integrations with supported apps. + +#### Supported integrations + +- **OpenCode** - Open-source coding assistant +- **Claude Code** - Anthropic's agentic coding tool +- **Codex** - OpenAI's coding assistant +- **Droid** - Factory's AI coding agent + +#### Examples + +Launch an integration interactively: + +``` +ollama launch +``` + +Launch a specific integration: + +``` +ollama launch claude +``` + +Launch with a specific model: + +``` +ollama launch claude --model qwen3-coder +``` + +Configure without launching: + +``` +ollama launch droid --config +``` + #### Multiline input For multiline input, you can wrap text with `"""`: diff --git a/docs/cloud.mdx b/docs/cloud.mdx index 4f4c3722b..4b2722e35 100644 --- a/docs/cloud.mdx +++ b/docs/cloud.mdx @@ -3,8 +3,6 @@ title: Cloud sidebarTitle: Cloud --- -Ollama's cloud is currently in preview. - ## Cloud Models Ollama's cloud models are a new kind of model in Ollama that can run without a powerful GPU. Instead, cloud models are automatically offloaded to Ollama's cloud service while offering the same capabilities as local models, making it possible to keep using your local tools while running larger models that wouldn't fit on a personal computer. diff --git a/docs/context-length.mdx b/docs/context-length.mdx index 43bcf0d31..6255bcd09 100644 --- a/docs/context-length.mdx +++ b/docs/context-length.mdx @@ -8,7 +8,7 @@ Context length is the maximum number of tokens that the model has access to in m The default context length in Ollama is 4096 tokens. -Tasks which require large context like web search, agents, and coding tools should be set to at least 32000 tokens. +Tasks which require large context like web search, agents, and coding tools should be set to at least 64000 tokens. ## Setting context length @@ -24,7 +24,7 @@ Change the slider in the Ollama app under settings to your desired context lengt ### CLI If editing the context length for Ollama is not possible, the context length can also be updated when serving Ollama. ``` -OLLAMA_CONTEXT_LENGTH=32000 ollama serve +OLLAMA_CONTEXT_LENGTH=64000 ollama serve ``` ### Check allocated context length and model offloading diff --git a/docs/docs.json b/docs/docs.json index 921c9e34e..9a6a8668f 100644 --- a/docs/docs.json +++ b/docs/docs.json @@ -102,18 +102,19 @@ "group": "Integrations", "pages": [ "/integrations/claude-code", - "/integrations/vscode", - "/integrations/jetbrains", - "/integrations/codex", "/integrations/cline", + "/integrations/codex", "/integrations/droid", "/integrations/goose", - "/integrations/zed", - "/integrations/roo-code", + "/integrations/jetbrains", + "/integrations/marimo", "/integrations/n8n", - "/integrations/xcode", "/integrations/onyx", - "/integrations/marimo" + "/integrations/opencode", + "/integrations/roo-code", + "/integrations/vscode", + "/integrations/xcode", + "/integrations/zed" ] }, { diff --git a/docs/index.mdx b/docs/index.mdx index 669d30cfb..ac1c744ea 100644 --- a/docs/index.mdx +++ b/docs/index.mdx @@ -9,7 +9,7 @@ sidebarTitle: Welcome - Get up and running with your first model + Get up and running with your first model or integrate Ollama with your favorite tools -``` - -3. Run Claude Code with a cloud model: - -```shell -claude --model glm-4.7:cloud -``` +**Note:** Claude Code requires a large context window. We recommend at least 64k tokens. See the [context length documentation](/context-length) for how to adjust context length in Ollama. ## Recommended Models -### Cloud models -- `glm-4.7:cloud` - High-performance cloud model -- `minimax-m2.1:cloud` - Fast cloud model -- `qwen3-coder:480b` - Large coding model +- `qwen3-coder` +- `glm-4.7` +- `gpt-oss:20b` +- `gpt-oss:120b` + +Cloud models are also available at [ollama.com/search?c=cloud](https://ollama.com/search?c=cloud). -### Local models -- `qwen3-coder` - Excellent for coding tasks -- `gpt-oss:20b` - Strong general-purpose model -- `gpt-oss:120b` - Larger general-purpose model for more complex tasks \ No newline at end of file diff --git a/docs/integrations/codex.mdx b/docs/integrations/codex.mdx index f9df1b858..7a79d39ab 100644 --- a/docs/integrations/codex.mdx +++ b/docs/integrations/codex.mdx @@ -13,7 +13,21 @@ npm install -g @openai/codex ## Usage with Ollama -Codex requires a larger context window. It is recommended to use a context window of at least 32K tokens. +Codex requires a larger context window. It is recommended to use a context window of at least 64k tokens. + +### Quick setup + +``` +ollama launch codex +``` + +To configure without launching: + +```shell +ollama launch codex --config +``` + +### Manual setup To use `codex` with Ollama, use the `--oss` flag: diff --git a/docs/integrations/droid.mdx b/docs/integrations/droid.mdx index b1ba37710..249554510 100644 --- a/docs/integrations/droid.mdx +++ b/docs/integrations/droid.mdx @@ -11,10 +11,24 @@ Install the [Droid CLI](https://factory.ai/): curl -fsSL https://app.factory.ai/cli | sh ``` -Droid requires a larger context window. It is recommended to use a context window of at least 32K tokens. See [Context length](/context-length) for more information. +Droid requires a larger context window. It is recommended to use a context window of at least 64k tokens. See [Context length](/context-length) for more information. ## Usage with Ollama +### Quick setup + +```bash +ollama launch droid +``` + +To configure without launching: + +```shell +ollama launch droid --config +``` + +### Manual setup + Add a local configuration block to `~/.factory/config.json`: ```json @@ -73,4 +87,4 @@ Add the cloud configuration block to `~/.factory/config.json`: } ``` -Run `droid` in a new terminal to load the new settings. \ No newline at end of file +Run `droid` in a new terminal to load the new settings. diff --git a/docs/integrations/opencode.mdx b/docs/integrations/opencode.mdx new file mode 100644 index 000000000..1bdbc3ab6 --- /dev/null +++ b/docs/integrations/opencode.mdx @@ -0,0 +1,106 @@ +--- +title: OpenCode +--- + +OpenCode is an open-source AI coding assistant that runs in your terminal. + +## Install + +Install the [OpenCode CLI](https://opencode.ai): + +```bash +curl -fsSL https://opencode.ai/install.sh | bash +``` + +OpenCode requires a larger context window. It is recommended to use a context window of at least 64k tokens. See [Context length](/context-length) for more information. + +## Usage with Ollama + +### Quick setup + +```bash +ollama launch opencode +``` + +To configure without launching: + +```shell +ollama launch opencode --config +``` + +### Manual setup + +Add a configuration block to `~/.config/opencode/opencode.json`: + +```json +{ + "$schema": "https://opencode.ai/config.json", + "provider": { + "ollama": { + "npm": "@ai-sdk/openai-compatible", + "name": "Ollama", + "options": { + "baseURL": "http://localhost:11434/v1" + }, + "models": { + "qwen3-coder": { + "name": "qwen3-coder" + } + } + } + } +} +``` + +## Cloud Models + +`glm-4.7:cloud` is the recommended model for use with OpenCode. + +Add the cloud configuration to `~/.config/opencode/opencode.json`: + +```json +{ + "$schema": "https://opencode.ai/config.json", + "provider": { + "ollama": { + "npm": "@ai-sdk/openai-compatible", + "name": "Ollama", + "options": { + "baseURL": "http://localhost:11434/v1" + }, + "models": { + "glm-4.7:cloud": { + "name": "glm-4.7:cloud" + } + } + } + } +} +``` + +## Connecting to ollama.com + +1. Create an [API key](https://ollama.com/settings/keys) from ollama.com and export it as `OLLAMA_API_KEY`. +2. Update `~/.config/opencode/opencode.json` to point to ollama.com: + +```json +{ + "$schema": "https://opencode.ai/config.json", + "provider": { + "ollama": { + "npm": "@ai-sdk/openai-compatible", + "name": "Ollama Cloud", + "options": { + "baseURL": "https://ollama.com/v1" + }, + "models": { + "glm-4.7:cloud": { + "name": "glm-4.7:cloud" + } + } + } + } +} +``` + +Run `opencode` in a new terminal to load the new settings. diff --git a/docs/quickstart.mdx b/docs/quickstart.mdx index 5ef9fa825..03ed130df 100644 --- a/docs/quickstart.mdx +++ b/docs/quickstart.mdx @@ -18,13 +18,13 @@ This quickstart will walk your through running your first model with Ollama. To Open a terminal and run the command: - ``` + ```sh ollama run gemma3 ``` - ``` + ```sh ollama pull gemma3 ``` @@ -45,13 +45,13 @@ This quickstart will walk your through running your first model with Ollama. To Start by downloading a model: - ``` + ```sh ollama pull gemma3 ``` Then install Ollama's Python library: - ``` + ```sh pip install ollama ``` @@ -101,3 +101,42 @@ This quickstart will walk your through running your first model with Ollama. To See a full list of available models [here](https://ollama.com/models). + +## Coding + +For coding use cases, we recommend using the `glm-4.7-flash` model. + +Note: this model requires 23 GB of VRAM with 64000 tokens context length. +```sh +ollama pull glm-4.7-flash +``` + +Alternatively, you can use a more powerful cloud model (with full context length): +```sh +ollama pull glm-4.7:cloud +``` + +Use `ollama launch` to quickly set up a coding tool with Ollama models: + +```sh +ollama launch +``` + +### Supported integrations + +- [OpenCode](/integrations/opencode) - Open-source coding assistant +- [Claude Code](/integrations/claude-code) - Anthropic's agentic coding tool +- [Codex](/integrations/codex) - OpenAI's coding assistant +- [Droid](/integrations/droid) - Factory's AI coding agent + +### Launch with a specific model + +```sh +ollama launch claude --model glm-4.7-flash +``` + +### Configure without launching + +```sh +ollama launch claude --config +```