wehub-resource-sync
3db29810ba
Update Stable Docs / update_stable_docs (push) Waiting to run
Test / test (macos-latest, 3.11, ) (push) Waiting to run
Test / test (macos-latest, 3.12, ) (push) Waiting to run
Test / test (macos-latest, 3.13, ) (push) Waiting to run
Test / test (ubuntu-latest, 3.10, ) (push) Waiting to run
Test / test (ubuntu-latest, 3.11, ) (push) Waiting to run
Test / test (ubuntu-latest, 3.12, ) (push) Waiting to run
Test / test (ubuntu-latest, 3.13, ) (push) Waiting to run
Test / test (ubuntu-latest, 3.14, ) (push) Waiting to run
Test / test (ubuntu-latest, 3.14, 4.0rc4) (push) Waiting to run
Test / test (windows-latest, 3.10, ) (push) Waiting to run
Test / test (windows-latest, 3.11, ) (push) Waiting to run
Test / test (windows-latest, 3.12, ) (push) Waiting to run
Test / test (macos-latest, 3.10, ) (push) Waiting to run
Test / test (macos-latest, 3.14, ) (push) Waiting to run
Test / test (windows-latest, 3.13, ) (push) Waiting to run
Test / test (windows-latest, 3.14, ) (push) Waiting to run
375 lines
28 KiB
Markdown
375 lines
28 KiB
Markdown
<!-- WEHUB_ZH_README -->
|
||
> [!NOTE]
|
||
> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。
|
||
> [English](./README.en.md) · [原始项目](https://github.com/simonw/llm) · [上游 README](https://github.com/simonw/llm/blob/HEAD/README.md)
|
||
> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。
|
||
|
||
<!-- [[[cog
|
||
# README.md is generated from docs/index.md using sphinx_markdown_builder
|
||
import tempfile
|
||
import subprocess
|
||
from pathlib import Path
|
||
|
||
readme_markdown = ''
|
||
|
||
with tempfile.TemporaryDirectory() as tmpdir:
|
||
tmp_path = Path(tmpdir)
|
||
# Run: sphinx-build -M markdown ./docs ./tmpdir
|
||
subprocess.run([
|
||
"sphinx-build",
|
||
"-M", "markdown",
|
||
"./docs",
|
||
str(tmp_path)
|
||
], check=True)
|
||
index_file = tmp_path / "markdown" / "index.md"
|
||
readme_markdown = index_file.read_text(encoding="utf-8")
|
||
|
||
cog.out(readme_markdown)
|
||
]]] -->
|
||
# LLM
|
||
|
||
[](https://github.com/simonw/llm)
|
||
[](https://pypi.org/project/llm/)
|
||
[](https://llm.datasette.io/en/stable/changelog.html)
|
||
[](https://github.com/simonw/llm/actions?query=workflow%3ATest)
|
||
[](https://github.com/simonw/llm/blob/main/LICENSE)
|
||
[](https://datasette.io/discord-llm)
|
||
[](https://formulae.brew.sh/formula/llm)
|
||
|
||
一款 CLI 工具和 Python 库，用于与 **OpenAI**、**Anthropic 的 Claude**、**Google 的 Gemini**、**Meta 的 Llama** 以及数十种其他大语言模型（Large Language Model，LLM）交互，既可通过远程 API，也可使用可在你本机安装和运行的模型。
|
||
|
||
在 YouTube 上观看 **[命令行上的语言模型](https://www.youtube.com/watch?v=QUXQNi6jQ30)** 演示，或[阅读配套的详细笔记](https://simonwillison.net/2024/Jun/17/cli-language-models/).
|
||
|
||
使用 LLM，你可以：
|
||
|
||
- [从命令行运行提示词](https://llm.datasette.io/en/stable/usage.html#usage-executing-prompts)
|
||
- [将提示词和响应存储在 SQLite 中](https://llm.datasette.io/en/stable/logging.html#logging)
|
||
- [生成并存储嵌入向量（embeddings）](https://llm.datasette.io/en/stable/embeddings/index.html#embeddings)
|
||
- [从文本和图像中提取结构化内容](https://llm.datasette.io/en/stable/schemas.html#schemas)
|
||
- [赋予模型执行工具的能力](https://llm.datasette.io/en/stable/tools.html#tools)
|
||
- … 以及更多、更多功能
|
||
|
||
## 快速入门
|
||
|
||
首先，使用 `pip` 或 Homebrew 或 `pipx` 或 `uv` 安装 LLM：
|
||
|
||
```bash
|
||
pip install llm
|
||
```
|
||
|
||
或使用 Homebrew（参见[警告说明](https://llm.datasette.io/en/stable/setup.html#homebrew-warning)):
|
||
|
||
```bash
|
||
brew install llm
|
||
```
|
||
|
||
或使用 [pipx](https://pypa.github.io/pipx/):
|
||
|
||
```bash
|
||
pipx install llm
|
||
```
|
||
|
||
或使用 [uv](https://docs.astral.sh/uv/guides/tools/)
|
||
|
||
```bash
|
||
uv tool install llm
|
||
```
|
||
|
||
如果你有 [OpenAI API 密钥](https://platform.openai.com/api-keys)，可以运行以下命令：
|
||
|
||
```bash
|
||
# Paste your OpenAI API key into this
|
||
llm keys set openai
|
||
|
||
# Run a prompt (with the default gpt-4o-mini model)
|
||
llm "Ten fun names for a pet pelican"
|
||
|
||
# Extract text from an image
|
||
llm "extract text" -a scanned-document.jpg
|
||
|
||
# Use a system prompt against a file
|
||
cat myfile.py | llm -s "Explain this code"
|
||
```
|
||
|
||
使用各自插件对 [Gemini](https://aistudio.google.com/apikey) 或 [Anthropic](https://console.anthropic.com/) 运行提示词：
|
||
|
||
```bash
|
||
llm install llm-gemini
|
||
llm keys set gemini
|
||
# Paste Gemini API key here
|
||
llm -m gemini-2.0-flash 'Tell me fun facts about Mountain View'
|
||
|
||
llm install llm-anthropic
|
||
llm keys set anthropic
|
||
# Paste Anthropic API key here
|
||
llm -m claude-4-opus 'Impress me with wild facts about turnips'
|
||
```
|
||
|
||
你还可以[安装插件](https://llm.datasette.io/en/stable/plugins/installing-plugins.html#installing-plugins) 以访问可在本地设备上运行的模型。如果你使用 [Ollama](https://ollama.com/):
|
||
|
||
```bash
|
||
# Install the plugin
|
||
llm install llm-ollama
|
||
|
||
# Download and run a prompt against the Orca Mini 7B model
|
||
ollama pull llama3.2:latest
|
||
llm -m llama3.2:latest 'What is the capital of France?'
|
||
```
|
||
|
||
要启动与模型的[交互式聊天](https://llm.datasette.io/en/stable/usage.html#usage-chat)，请使用 `llm chat`：
|
||
|
||
```bash
|
||
llm chat -m gpt-4.1
|
||
```
|
||
|
||
```default
|
||
Chatting with gpt-4.1
|
||
Type 'exit' or 'quit' to exit
|
||
Type '!multi' to enter multiple lines, then '!end' to finish
|
||
Type '!edit' to open your default editor and modify the prompt.
|
||
Type '!fragment <my_fragment> [<another_fragment> ...]' to insert one or more fragments
|
||
> Tell me a joke about a pelican
|
||
Why don't pelicans like to tip waiters?
|
||
|
||
Because they always have a big bill!
|
||
```
|
||
|
||
关于本项目的更多背景：
|
||
|
||
- [llm、ttok 和 strip-tags——用于 ChatGPT 及其他 LLM 的 CLI 工具](https://simonwillison.net/2023/May/18/cli-tools-for-llms/)
|
||
- [LLM CLI 工具现已通过插件支持自托管语言模型](https://simonwillison.net/2023/Jul/12/llm/)
|
||
- [LLM 现已提供用于处理嵌入向量的工具](https://simonwillison.net/2023/Sep/4/llm-embeddings/)
|
||
- [使用 llm-clip 构建图像搜索引擎，使用 llm chat 与模型对话](https://simonwillison.net/2023/Sep/12/llm-clip-and-chat/)
|
||
- [你现在可以在终端中使用 LLM 对图像、音频和视频运行提示词](https://simonwillison.net/2024/Oct/29/llm-multi-modal/)
|
||
- [使用 LLM 模式（schema）从非结构化内容中提取结构化数据](https://simonwillison.net/2025/Feb/28/llm-schemas/)
|
||
- [LLM 0.24 通过片段（fragment）和模板插件支持长上下文](https://simonwillison.net/2025/Apr/7/long-context-llm/)
|
||
|
||
另请参阅我博客上的 [llm 标签](https://simonwillison.net/tags/llm/)。
|
||
|
||
## 目录
|
||
|
||
* [设置](https://llm.datasette.io/en/stable/setup.html)
|
||
* [安装](https://llm.datasette.io/en/stable/setup.html#installation)
|
||
* [升级到最新版本](https://llm.datasette.io/en/stable/setup.html#upgrading-to-the-latest-version)
|
||
* [使用 uvx](https://llm.datasette.io/en/stable/setup.html#using-uvx)
|
||
* [关于 Homebrew 和 PyTorch 的说明](https://llm.datasette.io/en/stable/setup.html#a-note-about-homebrew-and-pytorch)
|
||
* [安装插件](https://llm.datasette.io/en/stable/setup.html#installing-plugins)
|
||
* [API 密钥管理](https://llm.datasette.io/en/stable/setup.html#api-key-management)
|
||
* [保存和使用已存储的密钥](https://llm.datasette.io/en/stable/setup.html#saving-and-using-stored-keys)
|
||
* [使用 –key 选项传递密钥](https://llm.datasette.io/en/stable/setup.html#passing-keys-using-the-key-option)
|
||
* [环境变量中的密钥](https://llm.datasette.io/en/stable/setup.html#keys-in-environment-variables)
|
||
* [配置](https://llm.datasette.io/en/stable/setup.html#configuration)
|
||
* [设置自定义默认模型](https://llm.datasette.io/en/stable/setup.html#setting-a-custom-default-model)
|
||
* [设置自定义目录位置](https://llm.datasette.io/en/stable/setup.html#setting-a-custom-directory-location)
|
||
* [开启和关闭 SQLite 日志记录](https://llm.datasette.io/en/stable/setup.html#turning-sqlite-logging-on-and-off)
|
||
* [用法](https://llm.datasette.io/en/stable/usage.html)
|
||
* [执行提示词](https://llm.datasette.io/en/stable/usage.html#executing-a-prompt)
|
||
* [模型选项](https://llm.datasette.io/en/stable/usage.html#model-options)
|
||
* [附件](https://llm.datasette.io/en/stable/usage.html#attachments)
|
||
* [系统提示词](https://llm.datasette.io/en/stable/usage.html#system-prompts)
|
||
* [工具](https://llm.datasette.io/en/stable/usage.html#tools)
|
||
* [提取围栏代码块](https://llm.datasette.io/en/stable/usage.html#extracting-fenced-code-blocks)
|
||
* [模式（Schema）](https://llm.datasette.io/en/stable/usage.html#schemas)
|
||
* [片段（Fragment）](https://llm.datasette.io/en/stable/usage.html#fragments)
|
||
* [继续对话](https://llm.datasette.io/en/stable/usage.html#continuing-a-conversation)
|
||
* [在 Bash 或 Zsh 中使用 LLM 的技巧](https://llm.datasette.io/en/stable/usage.html#tips-for-using-llm-with-bash-or-zsh)
|
||
* [补全提示词](https://llm.datasette.io/en/stable/usage.html#completion-prompts)
|
||
* [启动交互式聊天](https://llm.datasette.io/en/stable/usage.html#starting-an-interactive-chat)
|
||
* [列出可用模型](https://llm.datasette.io/en/stable/usage.html#listing-available-models)
|
||
* [为模型设置默认选项](https://llm.datasette.io/en/stable/usage.html#setting-default-options-for-models)
|
||
* [OpenAI 模型](https://llm.datasette.io/en/stable/openai-models.html)
|
||
* [配置](https://llm.datasette.io/en/stable/openai-models.html#configuration)
|
||
* [OpenAI 语言模型](https://llm.datasette.io/en/stable/openai-models.html#openai-language-models)
|
||
* [模型特性](https://llm.datasette.io/en/stable/openai-models.html#model-features)
|
||
* [OpenAI 嵌入模型](https://llm.datasette.io/en/stable/openai-models.html#openai-embedding-models)
|
||
* [OpenAI 补全模型](https://llm.datasette.io/en/stable/openai-models.html#openai-completion-models)
|
||
* [添加更多 OpenAI 模型](https://llm.datasette.io/en/stable/openai-models.html#adding-more-openai-models)
|
||
* [其他模型](https://llm.datasette.io/en/stable/other-models.html)
|
||
* [安装和使用本地模型](https://llm.datasette.io/en/stable/other-models.html#installing-and-using-a-local-model)
|
||
* [兼容 OpenAI 的模型](https://llm.datasette.io/en/stable/other-models.html#openai-compatible-models)
|
||
* [额外的 HTTP 标头](https://llm.datasette.io/en/stable/other-models.html#extra-http-headers)
|
||
* [工具](https://llm.datasette.io/en/stable/tools.html)
|
||
* [工具的工作原理](https://llm.datasette.io/en/stable/tools.html#how-tools-work)
|
||
* [试用工具](https://llm.datasette.io/en/stable/tools.html#trying-out-tools)
|
||
* [LLM 的工具实现](https://llm.datasette.io/en/stable/tools.html#llm-s-implementation-of-tools)
|
||
* [默认工具](https://llm.datasette.io/en/stable/tools.html#default-tools)
|
||
* [实现工具的技巧](https://llm.datasette.io/en/stable/tools.html#tips-for-implementing-tools)
|
||
* [模式（Schema）](https://llm.datasette.io/en/stable/schemas.html)
|
||
* [模式教程](https://llm.datasette.io/en/stable/schemas.html#schemas-tutorial)
|
||
* [从狗（dogs）示例入门](https://llm.datasette.io/en/stable/schemas.html#getting-started-with-dogs)
|
||
* [从新闻文章中提取人物](https://llm.datasette.io/en/stable/schemas.html#extracting-people-from-a-news-articles)
|
||
* [使用 JSON 模式](https://llm.datasette.io/en/stable/schemas.html#using-json-schemas)
|
||
* [指定模式的方式](https://llm.datasette.io/en/stable/schemas.html#ways-to-specify-a-schema)
|
||
* [简洁的 LLM 模式语法](https://llm.datasette.io/en/stable/schemas.html#concise-llm-schema-syntax)
|
||
* [在模板中保存可复用的模式](https://llm.datasette.io/en/stable/schemas.html#saving-reusable-schemas-in-templates)
|
||
* [浏览使用模式创建的已记录 JSON 对象](https://llm.datasette.io/en/stable/schemas.html#browsing-logged-json-objects-created-using-schemas)
|
||
* [模板](https://llm.datasette.io/en/stable/templates.html)
|
||
* [<code>–save</code> 入门](https://llm.datasette.io/en/stable/templates.html#getting-started-with-save)
|
||
* [使用模板](https://llm.datasette.io/en/stable/templates.html#using-a-template)
|
||
* [列出可用模板](https://llm.datasette.io/en/stable/templates.html#listing-available-templates)
|
||
* [作为 YAML 文件的模板](https://llm.datasette.io/en/stable/templates.html#templates-as-yaml-files)
|
||
* [系统提示词](https://llm.datasette.io/en/stable/templates.html#system-prompts)
|
||
* [片段](https://llm.datasette.io/en/stable/templates.html#fragments)
|
||
* [选项](https://llm.datasette.io/en/stable/templates.html#options)
|
||
* [工具](https://llm.datasette.io/en/stable/templates.html#tools)
|
||
* [模式](https://llm.datasette.io/en/stable/templates.html#schemas)
|
||
* [额外的模板变量](https://llm.datasette.io/en/stable/templates.html#additional-template-variables)
|
||
* [指定默认参数](https://llm.datasette.io/en/stable/templates.html#specifying-default-parameters)
|
||
* [配置代码提取](https://llm.datasette.io/en/stable/templates.html#configuring-code-extraction)
|
||
* [为模板设置默认模型](https://llm.datasette.io/en/stable/templates.html#setting-a-default-model-for-a-template)
|
||
* [来自插件的模板加载器](https://llm.datasette.io/en/stable/templates.html#template-loaders-from-plugins)
|
||
* [片段](https://llm.datasette.io/en/stable/fragments.html)
|
||
* [在提示词中使用片段](https://llm.datasette.io/en/stable/fragments.html#using-fragments-in-a-prompt)
|
||
* [在聊天中使用片段](https://llm.datasette.io/en/stable/fragments.html#using-fragments-in-chat)
|
||
* [浏览片段](https://llm.datasette.io/en/stable/fragments.html#browsing-fragments)
|
||
* [为片段设置别名](https://llm.datasette.io/en/stable/fragments.html#setting-aliases-for-fragments)
|
||
* [在日志中查看片段](https://llm.datasette.io/en/stable/fragments.html#viewing-fragments-in-your-logs)
|
||
* [使用来自插件的片段](https://llm.datasette.io/en/stable/fragments.html#using-fragments-from-plugins)
|
||
* [列出可用的片段前缀](https://llm.datasette.io/en/stable/fragments.html#listing-available-fragment-prefixes)
|
||
* [模型别名](https://llm.datasette.io/en/stable/aliases.html)
|
||
* [列出别名](https://llm.datasette.io/en/stable/aliases.html#listing-aliases)
|
||
* [添加新别名](https://llm.datasette.io/en/stable/aliases.html#adding-a-new-alias)
|
||
* [删除别名](https://llm.datasette.io/en/stable/aliases.html#removing-an-alias)
|
||
* [查看别名文件](https://llm.datasette.io/en/stable/aliases.html#viewing-the-aliases-file)
|
||
* [嵌入向量（Embeddings）](https://llm.datasette.io/en/stable/embeddings/index.html)
|
||
* [使用 CLI 生成嵌入](https://llm.datasette.io/en/stable/embeddings/cli.html)
|
||
* [llm embed](https://llm.datasette.io/en/stable/embeddings/cli.html#llm-embed)
|
||
* [llm embed-multi](https://llm.datasette.io/en/stable/embeddings/cli.html#llm-embed-multi)
|
||
* [llm similar](https://llm.datasette.io/en/stable/embeddings/cli.html#llm-similar)
|
||
* [llm embed-models](https://llm.datasette.io/en/stable/embeddings/cli.html#llm-embed-models)
|
||
* [llm collections list](https://llm.datasette.io/en/stable/embeddings/cli.html#llm-collections-list)
|
||
* [llm collections delete](https://llm.datasette.io/en/stable/embeddings/cli.html#llm-collections-delete)
|
||
* [从 Python 使用嵌入向量](https://llm.datasette.io/en/stable/embeddings/python-api.html)
|
||
* [使用集合](https://llm.datasette.io/en/stable/embeddings/python-api.html#working-with-collections)
|
||
* [检索相似项](https://llm.datasette.io/en/stable/embeddings/python-api.html#retrieving-similar-items)
|
||
* [SQL 模式](https://llm.datasette.io/en/stable/embeddings/python-api.html#sql-schema)
|
||
* [编写插件以添加新的嵌入模型](https://llm.datasette.io/en/stable/embeddings/writing-plugins.html)
|
||
* [`EmbeddingModel`](https://llm.datasette.io/en/stable/embeddings/writing-plugins.html#llm.EmbeddingModel)
|
||
* [嵌入二进制内容](https://llm.datasette.io/en/stable/embeddings/writing-plugins.html#embedding-binary-content)
|
||
* [嵌入存储格式](https://llm.datasette.io/en/stable/embeddings/storage.html)
|
||
* [插件](https://llm.datasette.io/en/stable/plugins/index.html)
|
||
* [安装插件](https://llm.datasette.io/en/stable/plugins/installing-plugins.html)
|
||
* [列出已安装的插件](https://llm.datasette.io/en/stable/plugins/installing-plugins.html#listing-installed-plugins)
|
||
* [使用部分插件运行](https://llm.datasette.io/en/stable/plugins/installing-plugins.html#running-with-a-subset-of-plugins)
|
||
* [插件目录](https://llm.datasette.io/en/stable/plugins/directory.html)
|
||
* [本地模型](https://llm.datasette.io/en/stable/plugins/directory.html#local-models)
|
||
* [远程 API](https://llm.datasette.io/en/stable/plugins/directory.html#remote-apis)
|
||
* [工具](https://llm.datasette.io/en/stable/plugins/directory.html#tools)
|
||
* [片段和模板加载器](https://llm.datasette.io/en/stable/plugins/directory.html#fragments-and-template-loaders)
|
||
* [嵌入模型](https://llm.datasette.io/en/stable/plugins/directory.html#embedding-models)
|
||
* [额外命令](https://llm.datasette.io/en/stable/plugins/directory.html#extra-commands)
|
||
* [仅供娱乐](https://llm.datasette.io/en/stable/plugins/directory.html#just-for-fun)
|
||
* [插件钩子](https://llm.datasette.io/en/stable/plugins/plugin-hooks.html)
|
||
* [register_commands(cli)](https://llm.datasette.io/en/stable/plugins/plugin-hooks.html#register-commands-cli)
|
||
* [register_models(register, model_aliases)](https://llm.datasette.io/en/stable/plugins/plugin-hooks.html#register-models-register-model-aliases)
|
||
* [register_embedding_models(register)](https://llm.datasette.io/en/stable/plugins/plugin-hooks.html#register-embedding-models-register)
|
||
* [register_tools(register)](https://llm.datasette.io/en/stable/plugins/plugin-hooks.html#register-tools-register)
|
||
* [register_template_loaders(register)](https://llm.datasette.io/en/stable/plugins/plugin-hooks.html#register-template-loaders-register)
|
||
* [register_fragment_loaders(register)](https://llm.datasette.io/en/stable/plugins/plugin-hooks.html#register-fragment-loaders-register)
|
||
* [开发模型插件](https://llm.datasette.io/en/stable/plugins/tutorial-model-plugin.html)
|
||
* [插件的初始结构](https://llm.datasette.io/en/stable/plugins/tutorial-model-plugin.html#the-initial-structure-of-the-plugin)
|
||
* [安装你的插件进行试用](https://llm.datasette.io/en/stable/plugins/tutorial-model-plugin.html#installing-your-plugin-to-try-it-out)
|
||
* [构建马尔可夫链](https://llm.datasette.io/en/stable/plugins/tutorial-model-plugin.html#building-the-markov-chain)
|
||
* [执行马尔可夫链](https://llm.datasette.io/en/stable/plugins/tutorial-model-plugin.html#executing-the-markov-chain)
|
||
* [将其添加到插件中](https://llm.datasette.io/en/stable/plugins/tutorial-model-plugin.html#adding-that-to-the-plugin)
|
||
* [理解 execute()](https://llm.datasette.io/en/stable/plugins/tutorial-model-plugin.html#understanding-execute)
|
||
* [提示词和响应会记录到数据库](https://llm.datasette.io/en/stable/plugins/tutorial-model-plugin.html#prompts-and-responses-are-logged-to-the-database)
|
||
* [添加选项](https://llm.datasette.io/en/stable/plugins/tutorial-model-plugin.html#adding-options)
|
||
* [分发你的插件](https://llm.datasette.io/en/stable/plugins/tutorial-model-plugin.html#distributing-your-plugin)
|
||
* [GitHub 仓库](https://llm.datasette.io/en/stable/plugins/tutorial-model-plugin.html#github-repositories)
|
||
* [将插件发布到 PyPI](https://llm.datasette.io/en/stable/plugins/tutorial-model-plugin.html#publishing-plugins-to-pypi)
|
||
* [添加元数据](https://llm.datasette.io/en/stable/plugins/tutorial-model-plugin.html#adding-metadata)
|
||
* [如果出现问题该怎么办](https://llm.datasette.io/en/stable/plugins/tutorial-model-plugin.html#what-to-do-if-it-breaks)
|
||
* [高级模型插件](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html)
|
||
* [技巧：懒加载昂贵的依赖项](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#tip-lazily-load-expensive-dependencies)
|
||
* [接受 API 密钥的模型](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#models-that-accept-api-keys)
|
||
* [异步模型](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#async-models)
|
||
* [支持模式](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#supporting-schemas)
|
||
* [支持工具](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#supporting-tools)
|
||
* [多模态模型的附件](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#attachments-for-multi-modal-models)
|
||
* [结构化消息和流式事件](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#structured-messages-and-streaming-events)
|
||
* [在 build_messages 中使用 prompt.messages](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#consuming-prompt-messages-in-build-messages)
|
||
* [在后续请求中恢复不透明元数据](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#restoring-opaque-metadata-on-subsequent-requests)
|
||
* [跟踪 token 使用量](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#tracking-token-usage)
|
||
* [跟踪解析后的模型名称](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#tracking-resolved-model-names)
|
||
* [LLM_RAISE_ERRORS](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#llm-raise-errors)
|
||
* [插件的实用函数](https://llm.datasette.io/en/stable/plugins/plugin-utilities.html)
|
||
* [llm.get_key()](https://llm.datasette.io/en/stable/plugins/plugin-utilities.html#llm-get-key)
|
||
* [llm.user_dir()](https://llm.datasette.io/en/stable/plugins/plugin-utilities.html#llm-user-dir)
|
||
* [llm.ModelError](https://llm.datasette.io/en/stable/plugins/plugin-utilities.html#llm-modelerror)
|
||
* [Response.fake()](https://llm.datasette.io/en/stable/plugins/plugin-utilities.html#response-fake)
|
||
* [Python API](https://llm.datasette.io/en/stable/python-api.html)
|
||
* [基本提示词执行](https://llm.datasette.io/en/stable/python-api.html#basic-prompt-execution)
|
||
* [系统提示词](https://llm.datasette.io/en/stable/python-api.html#system-prompts)
|
||
* [附件](https://llm.datasette.io/en/stable/python-api.html#attachments)
|
||
* [工具](https://llm.datasette.io/en/stable/python-api.html#tools)
|
||
* [模式](https://llm.datasette.io/en/stable/python-api.html#schemas)
|
||
* [片段](https://llm.datasette.io/en/stable/python-api.html#fragments)
|
||
* [模型选项](https://llm.datasette.io/en/stable/python-api.html#model-options)
|
||
* [传递 API 密钥](https://llm.datasette.io/en/stable/python-api.html#passing-an-api-key)
|
||
* [来自插件的模型](https://llm.datasette.io/en/stable/python-api.html#models-from-plugins)
|
||
* [访问底层 JSON](https://llm.datasette.io/en/stable/python-api.html#accessing-the-underlying-json)
|
||
* [Token 使用量](https://llm.datasette.io/en/stable/python-api.html#token-usage)
|
||
* [流式响应](https://llm.datasette.io/en/stable/python-api.html#streaming-responses)
|
||
* [结构化消息和流式事件](https://llm.datasette.io/en/stable/python-api.html#structured-messages-and-streaming-events)
|
||
* [异步模型](https://llm.datasette.io/en/stable/python-api.html#async-models)
|
||
* [`AsyncResponse`](https://llm.datasette.io/en/stable/python-api.html#llm.AsyncResponse)
|
||
* [工具函数可以是同步或异步的](https://llm.datasette.io/en/stable/python-api.html#tool-functions-can-be-sync-or-async)
|
||
* [异步模型的工具使用](https://llm.datasette.io/en/stable/python-api.html#tool-use-for-async-models)
|
||
* [对话](https://llm.datasette.io/en/stable/python-api.html#conversations)
|
||
* [使用工具的对话](https://llm.datasette.io/en/stable/python-api.html#conversations-using-tools)
|
||
* [列出模型](https://llm.datasette.io/en/stable/python-api.html#listing-models)
|
||
* [在响应完成时运行代码](https://llm.datasette.io/en/stable/python-api.html#running-code-when-a-response-has-completed)
|
||
* [其他函数](https://llm.datasette.io/en/stable/python-api.html#other-functions)
|
||
* [set_alias(alias, model_id)](https://llm.datasette.io/en/stable/python-api.html#set-alias-alias-model-id)
|
||
* [remove_alias(alias)](https://llm.datasette.io/en/stable/python-api.html#remove-alias-alias)
|
||
* [set_default_model(alias)](https://llm.datasette.io/en/stable/python-api.html#set-default-model-alias)
|
||
* [get_default_model()](https://llm.datasette.io/en/stable/python-api.html#get-default-model)
|
||
* [set_default_embedding_model(alias) and get_default_embedding_model()](https://llm.datasette.io/en/stable/python-api.html#set-default-embedding-model-alias-and-get-default-embedding-model)
|
||
* [记录到 SQLite](https://llm.datasette.io/en/stable/logging.html)
|
||
* [查看日志](https://llm.datasette.io/en/stable/logging.html#viewing-the-logs)
|
||
* [-s/–short 模式](https://llm.datasette.io/en/stable/logging.html#s-short-mode)
|
||
* [对话日志](https://llm.datasette.io/en/stable/logging.html#logs-for-a-conversation)
|
||
* [搜索日志](https://llm.datasette.io/en/stable/logging.html#searching-the-logs)
|
||
* [按特定 ID 之后的记录过滤](https://llm.datasette.io/en/stable/logging.html#filtering-past-a-specific-id)
|
||
* [按模型过滤](https://llm.datasette.io/en/stable/logging.html#filtering-by-model)
|
||
* [按使用了特定片段的提示词过滤](https://llm.datasette.io/en/stable/logging.html#filtering-by-prompts-that-used-specific-fragments)
|
||
* [按使用了特定工具的提示词过滤](https://llm.datasette.io/en/stable/logging.html#filtering-by-prompts-that-used-specific-tools)
|
||
* [浏览使用模式收集的数据](https://llm.datasette.io/en/stable/logging.html#browsing-data-collected-using-schemas)
|
||
* [使用 Datasette 浏览日志](https://llm.datasette.io/en/stable/logging.html#browsing-logs-using-datasette)
|
||
* [备份数据库](https://llm.datasette.io/en/stable/logging.html#backing-up-your-database)
|
||
* [SQL 模式](https://llm.datasette.io/en/stable/logging.html#sql-schema)
|
||
* [相关工具](https://llm.datasette.io/en/stable/related-tools.html)
|
||
* [strip-tags](https://llm.datasette.io/en/stable/related-tools.html#strip-tags)
|
||
* [ttok](https://llm.datasette.io/en/stable/related-tools.html#ttok)
|
||
* [Symbex](https://llm.datasette.io/en/stable/related-tools.html#symbex)
|
||
* [CLI 参考](https://llm.datasette.io/en/stable/help.html)
|
||
* [llm –help](https://llm.datasette.io/en/stable/help.html#llm-help)
|
||
* [llm prompt –help](https://llm.datasette.io/en/stable/help.html#llm-prompt-help)
|
||
* [llm chat –help](https://llm.datasette.io/en/stable/help.html#llm-chat-help)
|
||
* [llm keys –help](https://llm.datasette.io/en/stable/help.html#llm-keys-help)
|
||
* [llm logs –help](https://llm.datasette.io/en/stable/help.html#llm-logs-help)
|
||
* [llm models –help](https://llm.datasette.io/en/stable/help.html#llm-models-help)
|
||
* [llm templates –help](https://llm.datasette.io/en/stable/help.html#llm-templates-help)
|
||
* [llm schemas –help](https://llm.datasette.io/en/stable/help.html#llm-schemas-help)
|
||
* [llm tools –help](https://llm.datasette.io/en/stable/help.html#llm-tools-help)
|
||
* [llm aliases –help](https://llm.datasette.io/en/stable/help.html#llm-aliases-help)
|
||
* [llm fragments –help](https://llm.datasette.io/en/stable/help.html#llm-fragments-help)
|
||
* [llm plugins –help](https://llm.datasette.io/en/stable/help.html#llm-plugins-help)
|
||
* [llm install –help](https://llm.datasette.io/en/stable/help.html#llm-install-help)
|
||
* [llm uninstall –help](https://llm.datasette.io/en/stable/help.html#llm-uninstall-help)
|
||
* [llm embed –help](https://llm.datasette.io/en/stable/help.html#llm-embed-help)
|
||
* [llm embed-multi –help](https://llm.datasette.io/en/stable/help.html#llm-embed-multi-help)
|
||
* [llm similar –help](https://llm.datasette.io/en/stable/help.html#llm-similar-help)
|
||
* [llm embed-models –help](https://llm.datasette.io/en/stable/help.html#llm-embed-models-help)
|
||
* [llm collections –help](https://llm.datasette.io/en/stable/help.html#llm-collections-help)
|
||
* [llm openai –help](https://llm.datasette.io/en/stable/help.html#llm-openai-help)
|
||
* [贡献](https://llm.datasette.io/en/stable/contributing.html)
|
||
* [更新已记录的 HTTP API 交互及相关快照](https://llm.datasette.io/en/stable/contributing.html#updating-recorded-http-api-interactions-and-associated-snapshots)
|
||
* [调试技巧](https://llm.datasette.io/en/stable/contributing.html#debugging-tricks)
|
||
* [文档](https://llm.datasette.io/en/stable/contributing.html#documentation)
|
||
* [发布流程](https://llm.datasette.io/en/stable/contributing.html#release-process)
|
||
|
||
* [更新日志](https://llm.datasette.io/en/stable/changelog.html)
|
||
<!-- [[[end]]] -->
|