CLI 参考#

本页面列出了所有llm命令的--help输出。

llm –帮助#

Usage: llm [OPTIONS] COMMAND [ARGS]...

  Access Large Language Models from the command-line

  Documentation: https://llm.datasette.io/

  LLM can run models from many different providers. Consult the plugin directory
  for a list of available models:

  https://llm.datasette.io/en/stable/plugins/directory.html

  To get started with OpenAI, obtain an API key from them and:

      $ llm keys set openai
      Enter key: ...

  Then execute a prompt like this:

      llm 'Five outrageous names for a pet pelican'

Options:
  --version  Show the version and exit.
  --help     Show this message and exit.

Commands:
  prompt*       Execute a prompt
  aliases       Manage model aliases
  chat          Hold an ongoing chat with a model.
  collections   View and manage collections of embeddings
  embed         Embed text and store or return the result
  embed-models  Manage available embedding models
  embed-multi   Store embeddings for multiple strings at once
  install       Install packages from PyPI into the same environment as LLM
  keys          Manage stored API keys for different models
  logs          Tools for exploring logged prompts and responses
  models        Manage available models
  openai        Commands for working directly with the OpenAI API
  plugins       List installed plugins
  similar       Return top N similar IDs from a collection
  templates     Manage stored prompt templates
  uninstall     Uninstall Python packages from the LLM environment

llm prompt –帮助#

Usage: llm prompt [OPTIONS] [PROMPT]

  Execute a prompt

  Documentation: https://llm.datasette.io/en/stable/usage.html

  Examples:

      llm 'Capital of France?'
      llm 'Capital of France?' -m gpt-4o
      llm 'Capital of France?' -s 'answer in Spanish'

  Multi-modal models can be called with attachments like this:

      llm 'Extract text from this image' -a image.jpg
      llm 'Describe' -a https://static.simonwillison.net/static/2024/pelicans.jpg
      cat image | llm 'describe image' -a -
      # With an explicit mimetype:
      cat image | llm 'describe image' --at - image/jpeg

  The -x/--extract option returns just the content of the first ``` fenced code
  block, if one is present. If none are present it returns the full response.

      llm 'JavaScript function for reversing a string' -x

Options:
  -s, --system TEXT               System prompt to use
  -m, --model TEXT                Model to use
  -a, --attachment ATTACHMENT     Attachment path or URL or -
  --at, --attachment-type <TEXT TEXT>...
                                  Attachment with explicit mimetype
  -o, --option <TEXT TEXT>...     key/value options for the model
  -t, --template TEXT             Template to use
  -p, --param <TEXT TEXT>...      Parameters for template
  --no-stream                     Do not stream output
  -n, --no-log                    Don't log to database
  --log                           Log prompt and response to the database
  -c, --continue                  Continue the most recent conversation.
  --cid, --conversation TEXT      Continue the conversation with the given ID.
  --key TEXT                      API key to use
  --save TEXT                     Save prompt with this template name
  --async                         Run prompt asynchronously
  -u, --usage                     Show token usage
  -x, --extract                   Extract first fenced code block
  --xl, --extract-last            Extract last fenced code block
  --help                          Show this message and exit.

llm chat –帮助#

Usage: llm chat [OPTIONS]

  Hold an ongoing chat with a model.

Options:
  -s, --system TEXT            System prompt to use
  -m, --model TEXT             Model to use
  -c, --continue               Continue the most recent conversation.
  --cid, --conversation TEXT   Continue the conversation with the given ID.
  -t, --template TEXT          Template to use
  -p, --param <TEXT TEXT>...   Parameters for template
  -o, --option <TEXT TEXT>...  key/value options for the model
  --no-stream                  Do not stream output
  --key TEXT                   API key to use
  --help                       Show this message and exit.

llm keys –帮助#

Usage: llm keys [OPTIONS] COMMAND [ARGS]...

  Manage stored API keys for different models

Options:
  --help  Show this message and exit.

Commands:
  list*  List names of all stored keys
  get    Return the value of a stored key
  path   Output the path to the keys.json file
  set    Save a key in the keys.json file

llm 密钥列表 –帮助#

Usage: llm keys list [OPTIONS]

  List names of all stored keys

Options:
  --help  Show this message and exit.

llm 键路径 –help#

Usage: llm keys path [OPTIONS]

  Output the path to the keys.json file

Options:
  --help  Show this message and exit.

llm keys get –帮助#

Usage: llm keys get [OPTIONS] NAME

  Return the value of a stored key

  Example usage:

      export OPENAI_API_KEY=$(llm keys get openai)

Options:
  --help  Show this message and exit.

llm keys set –帮助#

Usage: llm keys set [OPTIONS] NAME

  Save a key in the keys.json file

  Example usage:

      $ llm keys set openai
      Enter key: ...

Options:
  --value TEXT  Value to set
  --help        Show this message and exit.

llm 日志 –帮助#

Usage: llm logs [OPTIONS] COMMAND [ARGS]...

  Tools for exploring logged prompts and responses

Options:
  --help  Show this message and exit.

Commands:
  list*   Show recent logged prompts and their responses
  off     Turn off logging for all prompts
  on      Turn on logging for all prompts
  path    Output the path to the logs.db file
  status  Show current status of database logging

llm 日志路径 –帮助#

Usage: llm logs path [OPTIONS]

  Output the path to the logs.db file

Options:
  --help  Show this message and exit.

llm 日志状态 –帮助#

Usage: llm logs status [OPTIONS]

  Show current status of database logging

Options:
  --help  Show this message and exit.

llm 日志开启 –帮助#

Usage: llm logs on [OPTIONS]

  Turn on logging for all prompts

Options:
  --help  Show this message and exit.

llm 注销 –帮助#

Usage: llm logs off [OPTIONS]

  Turn off logging for all prompts

Options:
  --help  Show this message and exit.

llm 日志列表 –帮助#

Usage: llm logs list [OPTIONS]

  Show recent logged prompts and their responses

Options:
  -n, --count INTEGER         Number of entries to show - defaults to 3, use 0
                              for all
  -p, --path FILE             Path to log database
  -m, --model TEXT            Filter by model or model alias
  -q, --query TEXT            Search for logs matching this string
  -t, --truncate              Truncate long strings in output
  -s, --short                 Shorter YAML output with truncated prompts
  -u, --usage                 Include token usage
  -r, --response              Just output the last response
  -x, --extract               Extract first fenced code block
  --xl, --extract-last        Extract last fenced code block
  -c, --current               Show logs from the current conversation
  --cid, --conversation TEXT  Show logs for this conversation ID
  --json                      Output logs as JSON
  --help                      Show this message and exit.

llm 模型 –帮助#

Usage: llm models [OPTIONS] COMMAND [ARGS]...

  Manage available models

Options:
  --help  Show this message and exit.

Commands:
  list*    List available models
  default  Show or set the default model

llm 模型列表 –帮助#

Usage: llm models list [OPTIONS]

  List available models

Options:
  --options         Show options for each model, if available
  --async           List async models
  -q, --query TEXT  Search for models matching these strings
  --help            Show this message and exit.

llm 模型默认 –帮助#

Usage: llm models default [OPTIONS] [MODEL]

  Show or set the default model

Options:
  --help  Show this message and exit.

llm 模板 –帮助#

Usage: llm templates [OPTIONS] COMMAND [ARGS]...

  Manage stored prompt templates

Options:
  --help  Show this message and exit.

Commands:
  list*  List available prompt templates
  edit   Edit the specified prompt template using the default $EDITOR
  path   Output the path to the templates directory
  show   Show the specified prompt template

llm 模板列表 –帮助#

Usage: llm templates list [OPTIONS]

  List available prompt templates

Options:
  --help  Show this message and exit.

llm 模板显示 –帮助#

Usage: llm templates show [OPTIONS] NAME

  Show the specified prompt template

Options:
  --help  Show this message and exit.

llm 模板编辑 –帮助#

Usage: llm templates edit [OPTIONS] NAME

  Edit the specified prompt template using the default $EDITOR

Options:
  --help  Show this message and exit.

llm 模板路径 –帮助#

Usage: llm templates path [OPTIONS]

  Output the path to the templates directory

Options:
  --help  Show this message and exit.

llm 别名 –帮助#

Usage: llm aliases [OPTIONS] COMMAND [ARGS]...

  Manage model aliases

Options:
  --help  Show this message and exit.

Commands:
  list*   List current aliases
  path    Output the path to the aliases.json file
  remove  Remove an alias
  set     Set an alias for a model

llm 别名列表 –帮助#

Usage: llm aliases list [OPTIONS]

  List current aliases

Options:
  --json  Output as JSON
  --help  Show this message and exit.

llm 别名设置 –帮助#

Usage: llm aliases set [OPTIONS] ALIAS [MODEL_ID]

  Set an alias for a model

  Example usage:

      llm aliases set mini gpt-4o-mini

  Alternatively you can omit the model ID and specify one or more -q options.
  The first model matching all of those query strings will be used.

      llm aliases set mini -q 4o -q mini

Options:
  -q, --query TEXT  Set alias for model matching these strings
  --help            Show this message and exit.

llm 别名移除 –帮助#

Usage: llm aliases remove [OPTIONS] ALIAS

  Remove an alias

  Example usage:

      $ llm aliases remove turbo

Options:
  --help  Show this message and exit.

llm 别名路径 –帮助#

Usage: llm aliases path [OPTIONS]

  Output the path to the aliases.json file

Options:
  --help  Show this message and exit.

llm 插件 –帮助#

Usage: llm plugins [OPTIONS]

  List installed plugins

Options:
  --all   Include built-in default plugins
  --help  Show this message and exit.

llm 安装 –帮助#

Usage: llm install [OPTIONS] [PACKAGES]...

  Install packages from PyPI into the same environment as LLM

Options:
  -U, --upgrade        Upgrade packages to latest version
  -e, --editable TEXT  Install a project in editable mode from this path
  --force-reinstall    Reinstall all packages even if they are already up-to-
                       date
  --no-cache-dir       Disable the cache
  --help               Show this message and exit.

llm 卸载 –帮助#

Usage: llm uninstall [OPTIONS] PACKAGES...

  Uninstall Python packages from the LLM environment

Options:
  -y, --yes  Don't ask for confirmation
  --help     Show this message and exit.

llm embed –帮助#

Usage: llm embed [OPTIONS] [COLLECTION] [ID]

  Embed text and store or return the result

Options:
  -i, --input PATH                File to embed
  -m, --model TEXT                Embedding model to use
  --store                         Store the text itself in the database
  -d, --database FILE
  -c, --content TEXT              Content to embed
  --binary                        Treat input as binary data
  --metadata TEXT                 JSON object metadata to store
  -f, --format [json|blob|base64|hex]
                                  Output format
  --help                          Show this message and exit.

llm embed-multi –帮助#

Usage: llm embed-multi [OPTIONS] COLLECTION [INPUT_PATH]

  Store embeddings for multiple strings at once

  Input can be CSV, TSV or a JSON list of objects.

  The first column is treated as an ID - all other columns are assumed to be
  text that should be concatenated together in order to calculate the
  embeddings.

  Input data can come from one of three sources:

  1. A CSV, JSON, TSV or JSON-nl file (including on standard input)
  2. A SQL query against a SQLite database
  3. A directory of files

Options:
  --format [json|csv|tsv|nl]   Format of input file - defaults to auto-detect
  --files <DIRECTORY TEXT>...  Embed files in this directory - specify directory
                               and glob pattern
  --encoding TEXT              Encoding to use when reading --files
  --binary                     Treat --files as binary data
  --sql TEXT                   Read input using this SQL query
  --attach <TEXT FILE>...      Additional databases to attach - specify alias
                               and file path
  --batch-size INTEGER         Batch size to use when running embeddings
  --prefix TEXT                Prefix to add to the IDs
  -m, --model TEXT             Embedding model to use
  --prepend TEXT               Prepend this string to all content before
                               embedding
  --store                      Store the text itself in the database
  -d, --database FILE
  --help                       Show this message and exit.

llm similar –帮助#

Usage: llm similar [OPTIONS] COLLECTION [ID]

  Return top N similar IDs from a collection

  Example usage:

      llm similar my-collection -c "I like cats"

  Or to find content similar to a specific stored ID:

      llm similar my-collection 1234

Options:
  -i, --input PATH      File to embed for comparison
  -c, --content TEXT    Content to embed for comparison
  --binary              Treat input as binary data
  -n, --number INTEGER  Number of results to return
  -d, --database FILE
  --help                Show this message and exit.

llm embed-models –帮助#

Usage: llm embed-models [OPTIONS] COMMAND [ARGS]...

  Manage available embedding models

Options:
  --help  Show this message and exit.

Commands:
  list*    List available embedding models
  default  Show or set the default embedding model

llm embed-models 列表 –帮助#

Usage: llm embed-models list [OPTIONS]

  List available embedding models

Options:
  -q, --query TEXT  Search for embedding models matching these strings
  --help            Show this message and exit.

llm embed-models 默认 –帮助#

Usage: llm embed-models default [OPTIONS] [MODEL]

  Show or set the default embedding model

Options:
  --remove-default  Reset to specifying no default model
  --help            Show this message and exit.

llm 集合 –帮助#

Usage: llm collections [OPTIONS] COMMAND [ARGS]...

  View and manage collections of embeddings

Options:
  --help  Show this message and exit.

Commands:
  list*   View a list of collections
  delete  Delete the specified collection
  path    Output the path to the embeddings database

llm collections 路径 –帮助#

Usage: llm collections path [OPTIONS]

  Output the path to the embeddings database

Options:
  --help  Show this message and exit.

llm 集合列表 –帮助#

Usage: llm collections list [OPTIONS]

  View a list of collections

Options:
  -d, --database FILE  Path to embeddings database
  --json               Output as JSON
  --help               Show this message and exit.

llm collections delete –帮助#

Usage: llm collections delete [OPTIONS] COLLECTION

  Delete the specified collection

  Example usage:

      llm collections delete my-collection

Options:
  -d, --database FILE  Path to embeddings database
  --help               Show this message and exit.

llm openai –帮助#

Usage: llm openai [OPTIONS] COMMAND [ARGS]...

  Commands for working directly with the OpenAI API

Options:
  --help  Show this message and exit.

Commands:
  models  List models available to you from the OpenAI API

llm openai models –帮助#

Usage: llm openai models [OPTIONS]

  List models available to you from the OpenAI API

Options:
  --json      Output as JSON
  --key TEXT  OpenAI API key
  --help      Show this message and exit.