orla_tips.md
| @@ -1,6 +1,8 @@ | |||
| 1 | 1 | ||
| 2 | 2 | # Orla | |
| 3 | 3 | ||
| 4 | + | https://github.com/dorcha-inc/orla | |
| 5 | + | ||
| 4 | 6 | Orla is a unix tool for running lightweight open-source agents. It is easy to add to a script, use with pipes, or build things on top of. | |
| 5 | 7 | ||
| 6 | 8 | ### Installing without local Ollama (docker or system) | |
orla_tips.md
| @@ -1,4 +1,6 @@ | |||
| 1 | 1 | ||
| 2 | + | # Orla | |
| 3 | + | ||
| 2 | 4 | Orla is a unix tool for running lightweight open-source agents. It is easy to add to a script, use with pipes, or build things on top of. | |
| 3 | 5 | ||
| 4 | 6 | ### Installing without local Ollama (docker or system) | |
orla.gif(檔案已創建)
Binary file changes are not shown
orla_tips.md(檔案已創建)
| @@ -0,0 +1,46 @@ | |||
| 1 | + | ||
| 2 | + | Orla is a unix tool for running lightweight open-source agents. It is easy to add to a script, use with pipes, or build things on top of. | |
| 3 | + | ||
| 4 | + | ### Installing without local Ollama (docker or system) | |
| 5 | + | ||
| 6 | + | If you already have a remote Ollama server or prefer to manage Ollama separately, you can skip the local Ollama installation: | |
| 7 | + | ||
| 8 | + | ||
| 9 | + | Using the install script: | |
| 10 | + | ```bash | |
| 11 | + | curl -fsSL https://raw.githubusercontent.com/dorcha-inc/orla/main/scripts/install.sh | sh -s -- --skip-ollama | |
| 12 | + | ``` | |
| 13 | + | ||
| 14 | + | After installation, configure Orla to use your remote Ollama server by setting either the `OLLAMA_HOST` or the `ORLA_OLLAMA_HOST` environment variable, or using the `llm_backend` configuration in your `orla.yaml`: | |
| 15 | + | ||
| 16 | + | ```bash | |
| 17 | + | export ORLA_OLLAMA_HOST=http://your-ollama-server:11434 | |
| 18 | + | ``` | |
| 19 | + | ||
| 20 | + | # Example Configuration | |
| 21 | + | Create an orla.yaml file in your project directory: | |
| 22 | + | ||
| 23 | + | ||
| 24 | + | ```yaml | |
| 25 | + | # Server mode configuration | |
| 26 | + | tools_dir: ./tools | |
| 27 | + | port: 8080 | |
| 28 | + | timeout: 30 | |
| 29 | + | log_format: json | |
| 30 | + | log_level: info | |
| 31 | + | ||
| 32 | + | # Agent mode configuration | |
| 33 | + | model: ollama:llama3 | |
| 34 | + | max_tool_calls: 10 | |
| 35 | + | streaming: true | |
| 36 | + | output_format: auto | |
| 37 | + | confirm_destructive: true | |
| 38 | + | show_thinking: false | |
| 39 | + | show_tool_calls: true | |
| 40 | + | ``` | |
| 41 | + | ||
| 42 | + | You can also set configuration via environment variables. For example: | |
| 43 | + | ||
| 44 | + | export ORLA_PORT=3000 | |
| 45 | + | export ORLA_MODEL=ollama:qwen3:1.7b | |
| 46 | + | export ORLA_SHOW_TOOL_CALLS=true | |