0.17a0

Alpha support for attachments, allowing multi-modal models to accept images, audio, video and other formats. #578

Attachments in the CLI can be URLs:

llm "describe this image" \
  -a https://static.simonwillison.net/static/2024/pelicans.jpg

Or file paths:

llm "extract text" -a image1.jpg -a image2.jpg

Or binary data, which may need to use --attachment-type to specify the MIME type:

cat image | llm "extract text" --attachment-type - image/jpeg

Attachments are also available in the Python API:

model = llm.get_model("gpt-4o-mini")
response = model.prompt(
    "Describe these images",
    attachments=[
        llm.Attachment(path="pelican.jpg"),
        llm.Attachment(url="https://static.simonwillison.net/static/2024/pelicans.jpg"),
    ]
)

Plugins that provide alternative models can support attachments, see Attachments for multi-modal models for details.

0.16

• OpenAI models now use the internal self.get_key() mechanism, which means they can be used from Python code in a way that will pick up keys that have been configured using llm keys set or the OPENAI_API_KEY environment variable. #552. This code now works correctly:

  import llm
  print(llm.get_model("gpt-4o-mini").prompt("hi"))

• New documented API methods: llm.get_default_model(), llm.set_default_model(alias), llm.get_default_embedding_model(alias), llm.set_default_embedding_model(). #553
• Support for OpenAI's new o1 family of preview models, llm -m o1-preview "prompt" and llm -m o1-mini "prompt". These models are currently only available to tier 5 OpenAI API users, though this may change in the future. #570

0.15

• Support for OpenAI's new GPT-4o mini model: llm -m gpt-4o-mini 'rave about pelicans in French' #536
• gpt-4o-mini is now the default model if you do not specify your own default, replacing GPT-3.5 Turbo. GPT-4o mini is both cheaper and better than GPT-3.5 Turbo.
• Fixed a bug where llm logs -q 'flourish' -m haiku could not combine both the -q search query and the -m model specifier. #515

0.14

• Support for OpenAI's new GPT-4o model: llm -m gpt-4o 'say hi in Spanish' #490
• The gpt-4-turbo alias is now a model ID, which indicates the latest version of OpenAI's GPT-4 Turbo text and image model. Your existing logs.db database may contain records under the previous model ID of gpt-4-turbo-preview. #493
• New llm logs -r/--response option for outputting just the last captured response, without wrapping it in Markdown and accompanying it with the prompt. #431
• Nine new {ref}plugins <plugin-directory> since version 0.13:
  • llm-claude-3 supporting Anthropic's Claude 3 family of models.
  • llm-command-r supporting Cohere's Command R and Command R Plus API models.
  • llm-reka supports the Reka family of models via their API.
  • llm-perplexity by Alexandru Geana supporting the Perplexity Labs API models, including llama-3-sonar-large-32k-online which can search for things online and llama-3-70b-instruct.
  • llm-groq by Moritz Angermann providing access to fast models hosted by Groq.
  • llm-fireworks supporting models hosted by Fireworks AI.
  • llm-together adds support for the Together AI extensive family of hosted openly licensed models.
  • llm-embed-onnx provides seven embedding models that can be executed using the ONNX model framework.
  • llm-cmd accepts a prompt for a shell command, runs that prompt and populates the result in your shell so you can review it, edit it and then hit <enter> to execute or ctrl+c to cancel, see this post for details.

0.13.1

• Fix for No module named 'readline' error on Windows. #407

0.13

See also LLM 0.13: The annotated release notes.

• Added support for new OpenAI embedding models: 3-small and 3-large and three variants of those with different dimension sizes, 3-small-512, 3-large-256 and 3-large-1024. See OpenAI embedding models for details. #394
• The default gpt-4-turbo model alias now points to gpt-4-turbo-preview, which uses the most recent OpenAI GPT-4 turbo model (currently gpt-4-0125-preview). #396
• New OpenAI model aliases gpt-4-1106-preview and gpt-4-0125-preview.
• OpenAI models now support a -o json_object 1 option which will cause their output to be returned as a valid JSON object. #373
• New plugins since the last release include llm-mistral, llm-gemini, llm-ollama and llm-bedrock-meta.
• The keys.json file for storing API keys is now created with 600 file permissions. #351
• Documented a pattern for installing plugins that depend on PyTorch using the Homebrew version of LLM, despite Homebrew using Python 3.12 when PyTorch have not yet released a stable package for that Python version. #397
• Underlying OpenAI Python library has been upgraded to >1.0. It is possible this could cause compatibility issues with LLM plugins that also depend on that library. #325
• Arrow keys now work inside the llm chat command. #376
• LLM_OPENAI_SHOW_RESPONSES=1 environment variable now outputs much more detailed information about the HTTP request and response made to OpenAI (and OpenAI-compatible) APIs. #404
• Dropped support for Python 3.7.

0.12

• Support for the new GPT-4 Turbo model from OpenAI. Try it using llm chat -m gpt-4-turbo or llm chat -m 4t. #323
• New -o seed 1 option for OpenAI models which sets a seed that can attempt to evaluate the prompt deterministically. #324

0.11.2

• Pin to version of OpenAI Python library prior to 1.0 to avoid breaking. #327

0.11.1

• Fixed a bug where llm embed -c "text" did not correctly pick up the configured default embedding model. #317
• New plugins: llm-python, llm-bedrock-anthropic and llm-embed-jina (described in Execute Jina embeddings with a CLI using llm-embed-jina).
• llm-gpt4all now uses the new GGUF model format. simonw/llm-gpt4all#16

0.11

LLM now supports the new OpenAI gpt-3.5-turbo-instruct model, and OpenAI completion (as opposed to chat completion) models in general. #284

llm -m gpt-3.5-turbo-instruct 'Reasons to tame a wild beaver:'

OpenAI completion models like this support a -o logprobs 3 option, which accepts a number between 1 and 5 and will include the log probabilities (for each produced token, what were the top 3 options considered by the model) in the logged response.

llm -m gpt-3.5-turbo-instruct 'Say hello succinctly' -o logprobs 3

You can then view the logprobs that were recorded in the SQLite logs database like this:

sqlite-utils "$(llm logs path)" \
  'select * from responses order by id desc limit 1' | \
  jq '.[0].response_json' -r | jq

Truncated output looks like this:

  [
    {
      "text": "Hi",
      "top_logprobs": [
        {
          "Hi": -0.13706253,
          "Hello": -2.3714375,
          "Hey": -3.3714373
        }
      ]
    },
    {
      "text": " there",
      "top_logprobs": [
        {
          " there": -0.96057636,
          "!\"": -0.5855763,
          ".\"": -3.2574513
        }
      ]
    }
  ]

Also in this release:

• The llm.user_dir() function, used by plugins, now ensures the directory exists before returning it. #275
• New LLM_OPENAI_SHOW_RESPONSES=1 environment variable for displaying the full HTTP response returned by OpenAI compatible APIs. #286
• The llm embed-multi command now has a --batch-size X option for setting the batch size to use when processing embeddings - useful if you have limited memory available. #273
• The collection.embed_multi() method also now accepts an optional batch_size=int argument.
• Fixed two bugs with llm embed-multi --files relating to handling of directories. Thanks, ealvar3z. #274, #280