diff --git a/website/docs/llms/ollama.md b/website/docs/llms/ollama.md index 49d729b9..10a09bd5 100644 --- a/website/docs/llms/ollama.md +++ b/website/docs/llms/ollama.md @@ -1,6 +1,6 @@ # Ollama -## How to use Ollama LLM and embedding API +## How to use Ollama LLM API 1. Go to [Ollama](https://github.com/jmorganca/ollama) and follow the instructions to set up a LLM model on your local environment. We recommend deploying the LLM with a parameter scale exceeding 13 billion for enhanced performance. @@ -10,10 +10,8 @@ We recommend deploying the LLM with a parameter scale exceeding 13 billion for e "llm.api_base": "http://localhost:11434", "llm.api_key": "ARBITRARY_STRING", "llm.api_type": "ollama", - "llm.model": "llama2:13b", - "llm.embedding_api_type": "ollama", - "llm.embedding_model": "llama2" + "llm.model": "llama2:13b" } ``` -NOTE: `llm.api_base` is the base URL set in the Ollama LLM API. +NOTE: `llm.api_base` is the URL started in the Ollama LLM server and `llm.model` is the model name of Ollama LLM. 3. Start TaskWeaver and chat with TaskWeaver. \ No newline at end of file diff --git a/website/docs/llms/qwen.md b/website/docs/llms/qwen.md index e1889d68..0436f2bc 100644 --- a/website/docs/llms/qwen.md +++ b/website/docs/llms/qwen.md @@ -1,8 +1,6 @@ # QWen -TaskWeaver supports QWen LLM and embedding API. - -## How to use QWen LLM and embedding API +## How to use QWen API 1. Go to [QWen](https://help.aliyun.com/zh/dashscope/developer-reference/activate-dashscope-and-create-an-api-key?spm=a2c4g.11186623.0.0.7b5749d72j3SYU) and register an account and get the API key. 2. Run `pip install dashscope` to install the required packages. @@ -11,12 +9,10 @@ TaskWeaver supports QWen LLM and embedding API. { "llm.api_type": "qwen", "llm.model": "qwen-max", - "llm.api_key": "YOUR_API_KEY", - "llm.embedding_api_type": "qwen", - "llm.embedding_model": "text-embedding-v1" + "llm.api_key": "YOUR_API_KEY" } ``` -NOTE: `llm.model` is the model name of QWen LLM and `llm.embedding_model` is the model name of QWen embedding API. +NOTE: `llm.model` is the model name of QWen LLM API. You can find the model name in the [QWen LLM model list](https://help.aliyun.com/zh/dashscope/developer-reference/model-square/?spm=a2c4g.11186623.0.0.35a36ffdt97ljI). 4. Start TaskWeaver and chat with TaskWeaver. \ No newline at end of file diff --git a/website/docs/llms/embedding.md b/website/docs/plugin/embedding.md similarity index 100% rename from website/docs/llms/embedding.md rename to website/docs/plugin/embedding.md diff --git a/website/docs/plugin/plugin_selection.md b/website/docs/plugin/plugin_selection.md index f2465302..710ddf2a 100644 --- a/website/docs/plugin/plugin_selection.md +++ b/website/docs/plugin/plugin_selection.md @@ -15,7 +15,7 @@ NOTE: the automatic plugin selection mechanism is only activated during the code At the start of TaskWeaver initialization, the automatic plugin selector is activated to generate embedding vectors for all plugins, including their names and descriptions. The embedding vectors are created using the specified embedding model configured in the `taskweaver_config.json` file. -For more information, please refer to the [embedding](../llms/embedding.md) documentation. +For more information, please refer to the [embedding](embedding.md) documentation. When the Planner sends a request to the Code Interpreter, the auto plugin selection mechanism will be triggered. It will first generate an embedding vector for the request using the same embedding model. diff --git a/website/sidebars.js b/website/sidebars.js index 154f8584..082cad94 100644 --- a/website/sidebars.js +++ b/website/sidebars.js @@ -26,7 +26,7 @@ const sidebars = { label: 'LLMs', collapsible: true, collapsed: false, - items: ['llms/index', 'llms/openai', 'llms/liteLLM'], + items: ['llms/index', 'llms/openai', 'llms/liteLLM', 'llms/ollama', 'llms/geni', 'llms/qwen'], }, {