Changelog#

0.13.1 (2024-01-26)#

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

0.13 (2024-01-26)#

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 (2023-11-06)#

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 (2023-11-06)#

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

0.11.1 (2023-10-31)#

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 (2023-09-18)#

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

0.10 (2023-09-12)#

The two major features in this release are the llm chat command and support for embedding binary data.

See Build an image search engine with llm-clip, chat with models with llm chat for more background on these features.

llm chat#

The new llm chat command starts an ongoing chat conversation with a model in your terminal. It works with all models supported by LLM and its plugins, including locally installed models such as Llama 2. #231

This offers a big performance boost for local models, since they don’t need to be freshly loaded into memory for each prompt.

Here’s an example chat with Llama 2 13B, provided by the llm-mlc plugin.

llm chat -m mlc-chat-Llama-2-13b-chat-hf-q4f16_1

This starts a chat session:

Type 'exit' or 'quit' to exit
Type '!multi' to enter multiple lines, then '!end' to finish
> Who are you?
Hello! I'm just an AI, here to assist you with any questions you may have.
My name is LLaMA, and I'm a large language model trained to provide helpful
and informative responses to a wide range of questions and topics. I'm here
to help you find the information you need, while ensuring a safe and
respectful conversation. Please feel free to ask me anything, and I'll do my
best to provide a helpful and accurate response.
> Tell me a joke about otters
Sure, here's a joke about otters:

Why did the otter go to the party?

Because he heard it was a "whale" of a time!

(Get it? Whale, like a big sea mammal, but also a "wild" or "fun" time.
Otters are known for their playful and social nature, so it's a lighthearted
and silly joke.)

I hope that brought a smile to your face! Do you have any other questions or
topics you'd like to discuss?
> exit

Chat sessions are logged to SQLite - use llm logs to view them. They can accept system prompts, templates and model options - consult the chat documentation for details.

Binary embedding support#

LLM’s embeddings feature has been expanded to provide support for embedding binary data, in addition to text. #254

This enables models like CLIP, supported by the new llm-clip plugin.

CLIP is a multi-modal embedding model which can embed images and text into the same vector space. This means you can use it to create an embedding index of photos, and then search for the embedding vector for “a happy dog” and get back images that are semantically closest to that string.

To create embeddings for every JPEG in a directory stored in a photos collection, run:

llm install llm-clip
llm embed-multi photos --files photos/ '*.jpg' --binary -m clip

Now you can search for photos of racoons using:

llm similar photos -c 'raccoon'

This spits out a list of images, ranked by how similar they are to the string “raccoon”:

{"id": "IMG_4801.jpeg", "score": 0.28125139257127457, "content": null, "metadata": null}
{"id": "IMG_4656.jpeg", "score": 0.26626441704164294, "content": null, "metadata": null}
{"id": "IMG_2944.jpeg", "score": 0.2647445926996852, "content": null, "metadata": null}
...

Also in this release#

The LLM_LOAD_PLUGINS environment variable can be used to control which plugins are loaded when llm starts running. #256
The llm plugins --all option includes builtin plugins in the list of plugins. #259
The llm embed-db family of commands has been renamed to llm collections. #229
llm embed-multi --files now has an --encoding option and defaults to falling back to latin-1 if a file cannot be processed as utf-8. #225

0.10a1 (2023-09-11)#

Support for embedding binary data. #254
llm chat now works for models with API keys. #247
llm chat -o for passing options to a model. #244
llm chat --no-stream option. #248
LLM_LOAD_PLUGINS environment variable. #256
llm plugins --all option for including builtin plugins. #259
llm embed-db has been renamed to llm collections. #229
Fixed bug where llm embed -c option was treated as a filepath, not a string. Thanks, mhalle. #263

0.10a0 (2023-09-04)#

New llm chat command for starting an interactive terminal chat with a model. #231
llm embed-multi --files now has an --encoding option and defaults to falling back to latin-1 if a file cannot be processed as utf-8. #225

0.9 (2023-09-03)#

The big new feature in this release is support for embeddings. See LLM now provides tools for working with embeddings for additional details.

Embedding models take a piece of text - a word, sentence, paragraph or even a whole article, and convert that into an array of floating point numbers. #185

This embedding vector can be thought of as representing a position in many-dimensional-space, where the distance between two vectors represents how semantically similar they are to each other within the content of a language model.

Embeddings can be used to find related documents, and also to implement semantic search - where a user can search for a phrase and get back results that are semantically similar to that phrase even if they do not share any exact keywords.

LLM now provides both CLI and Python APIs for working with embeddings. Embedding models are defined by plugins, so you can install additional models using the plugins mechanism.

The first two embedding models supported by LLM are:

OpenAI’s ada-002 embedding model, available via an inexpensive API if you set an OpenAI key using llm keys set openai.
The sentence-transformers family of models, available via the new llm-sentence-transformers plugin.

See Embedding with the CLI for detailed instructions on working with embeddings using LLM.

The new commands for working with embeddings are:

llm embed - calculate embeddings for content and return them to the console or store them in a SQLite database.
llm embed-multi - run bulk embeddings for multiple strings, using input from a CSV, TSV or JSON file, data from a SQLite database or data found by scanning the filesystem. #215
llm similar - run similarity searches against your stored embeddings - starting with a search phrase or finding content related to a previously stored vector. #190
llm embed-models - list available embedding models.
llm embed-db - commands for inspecting and working with the default embeddings SQLite database.

There’s also a new llm.Collection class for creating and searching collections of embedding from Python code, and a llm.get_embedding_model() interface for embedding strings directly. #191

0.8.1 (2023-08-31)#

Fixed bug where first prompt would show an error if the io.datasette.llm directory had not yet been created. #193
Updated documentation to recommend a different llm-gpt4all model since the one we were using is no longer available. #195

0.8 (2023-08-20)#

The output format for llm logs has changed. Previously it was JSON - it’s now a much more readable Markdown format suitable for pasting into other documents. #160
- The new llm logs --json option can be used to get the old JSON format.
- Pass llm logs --conversation ID or --cid ID to see the full logs for a specific conversation.
You can now combine piped input and a prompt in a single command: cat script.py | llm 'explain this code'. This works even for models that do not support system prompts. #153
Additional OpenAI-compatible models can now be configured with custom HTTP headers. This enables platforms such as openrouter.ai to be used with LLM, which can provide Claude access even without an Anthropic API key.
Keys set in keys.json are now used in preference to environment variables. #158
The documentation now includes a plugin directory listing all available plugins for LLM. #173
New related tools section in the documentation describing ttok, strip-tags and symbex. #111
The llm models, llm aliases and llm templates commands now default to running the same command as llm models list and llm aliases list and llm templates list. #167
New llm keys (aka llm keys list) command for listing the names of all configured keys. #174
Two new Python API functions, llm.set_alias(alias, model_id) and llm.remove_alias(alias) can be used to configure aliases from within Python code. #154
LLM is now compatible with both Pydantic 1 and Pydantic 2. This means you can install llm as a Python dependency in a project that depends on Pydantic 1 without running into dependency conflicts. Thanks, Chris Mungall. #147
llm.get_model(model_id) is now documented as raising llm.UnknownModelError if the requested model does not exist. #155

0.7.1 (2023-08-19)#

Fixed a bug where some users would see an AlterError: No such column: log.id error when attempting to use this tool, after upgrading to the latest sqlite-utils 3.35 release. #162

0.7 (2023-08-12)#

The new Model aliases commands can be used to configure additional aliases for models, for example:

llm aliases set turbo gpt-3.5-turbo-16k

Now you can run the 16,000 token gpt-3.5-turbo-16k model like this:

llm -m turbo 'An epic Greek-style saga about a cheesecake that builds a SQL database from scratch'

Use llm aliases list to see a list of aliases and llm aliases remove turbo to remove one again. #151

Notable new plugins#

llm-mlc can run local models released by the MLC project, including models that can take advantage of the GPU on Apple Silicon M1/M2 devices.
llm-llama-cpp uses llama.cpp to run models published in the GGML format. See Run Llama 2 on your own Mac using LLM and Homebrew for more details.

Also in this release#

OpenAI models now have min and max validation on their floating point options. Thanks, Pavel Král. #115
Fix for bug where llm templates list raised an error if a template had an empty prompt. Thanks, Sherwin Daganato. #132
Fixed bug in llm install --editable option which prevented installation of .[test]. #136
llm install --no-cache-dir and --force-reinstall options. #146

0.6.1 (2023-07-24)#

LLM can now be installed directly from Homebrew core: brew install llm. #124
Python API documentation now covers System prompts.
Fixed incorrect example in the Prompt templates documentation. Thanks, Jorge Cabello. #125

0.6 (2023-07-18)#

Models hosted on Replicate can now be accessed using the llm-replicate plugin, including the new Llama 2 model from Meta AI. More details here: Accessing Llama 2 from the command-line with the llm-replicate plugin.
Model providers that expose an API that is compatible with the OpenAPI API format, including self-hosted model servers such as LocalAI, can now be accessed using additional configuration for the default OpenAI plugin. #106
OpenAI models that are not yet supported by LLM can also be configured using the new extra-openai-models.yaml configuration file. #107
The llm logs command now accepts a -m model_id option to filter logs to a specific model. Aliases can be used here in addition to model IDs. #108
Logs now have a SQLite full-text search index against their prompts and responses, and the llm logs -q SEARCH option can be used to return logs that match a search term. #109

0.5 (2023-07-12)#

LLM now supports additional language models, thanks to a new plugins mechanism for installing additional models.

Plugins are available for 19 models in addition to the default OpenAI ones:

llm-gpt4all adds support for 17 models that can download and run on your own device, including Vicuna, Falcon and wizardLM.
llm-mpt30b adds support for the MPT-30B model, a 19GB download.
llm-palm adds support for Google’s PaLM 2 via the Google API.

A comprehensive tutorial, writing a plugin to support a new model describes how to add new models by building plugins in detail.

New features#

Python API documentation for using LLM models, including models from plugins, directly from Python. #75
Messages are now logged to the database by default - no need to run the llm init-db command any more, which has been removed. Instead, you can toggle this behavior off using llm logs off or turn it on again using llm logs on. The llm logs status command shows the current status of the log database. If logging is turned off, passing --log to the llm prompt command will cause that prompt to be logged anyway. #98
New database schema for logged messages, with conversations and responses tables. If you have previously used the old logs table it will continue to exist but will no longer be written to. #91
New -o/--option name value syntax for setting options for models, such as temperature. Available options differ for different models. #63
llm models list --options command for viewing all available model options. #82
llm "prompt" --save template option for saving a prompt directly to a template. #55
Prompt templates can now specify default values for parameters. Thanks, Chris Mungall. #57
llm openai models command to list all available OpenAI models from their API. #70
llm models default MODEL_ID to set a different model as the default to be used when llm is run without the -m/--model option. #31

Smaller improvements#

llm -s is now a shortcut for llm --system. #69
llm -m 4-32k alias for gpt-4-32k.
llm install -e directory command for installing a plugin from a local directory.
The LLM_USER_PATH environment variable now controls the location of the directory in which LLM stores its data. This replaces the old LLM_KEYS_PATH and LLM_LOG_PATH and LLM_TEMPLATES_PATH variables. #76
Documentation covering Utility functions for plugins.
Documentation site now uses Plausible for analytics. #79

0.4.1 (2023-06-17)#

LLM can now be installed using Homebrew: brew install simonw/llm/llm. #50
llm is now styled LLM in the documentation. #45
Examples in documentation now include a copy button. #43
llm templates command no longer has its display disrupted by newlines. #42
llm templates command now includes system prompt, if set. #44

0.4 (2023-06-17)#

This release includes some backwards-incompatible changes:

The -4 option for GPT-4 is now -m 4.
The --code option has been removed.
The -s option has been removed as streaming is now the default. Use --no-stream to opt out of streaming.

Prompt templates#

Prompt templates is a new feature that allows prompts to be saved as templates and re-used with different variables.

Templates can be created using the llm templates edit command:

llm templates edit summarize

Templates are YAML - the following template defines summarization using a system prompt:

system: Summarize this text

The template can then be executed like this:

cat myfile.txt | llm -t summarize

Templates can include both system prompts, regular prompts and indicate the model they should use. They can reference variables such as $input for content piped to the tool, or other variables that are passed using the new -p/--param option.

This example adds a voice parameter:

system: Summarize this text in the voice of $voice

Then to run it (via strip-tags to remove HTML tags from the input):

curl -s 'https://til.simonwillison.net/macos/imovie-slides-and-audio' | \
  strip-tags -m | llm -t summarize -p voice GlaDOS

Example output:

My previous test subject seemed to have learned something new about iMovie. They exported keynote slides as individual images […] Quite impressive for a human.

The Prompt templates documentation provides more detailed examples.

Continue previous chat#

You can now use llm to continue a previous conversation with the OpenAI chat models (gpt-3.5-turbo and gpt-4). This will include your previous prompts and responses in the prompt sent to the API, allowing the model to continue within the same context.

Use the new -c/--continue option to continue from the previous message thread:

llm "Pretend to be a witty gerbil, say hi briefly"

Greetings, dear human! I am a clever gerbil, ready to entertain you with my quick wit and endless energy.

llm "What do you think of snacks?" -c

Oh, how I adore snacks, dear human! Crunchy carrot sticks, sweet apple slices, and chewy yogurt drops are some of my favorite treats. I could nibble on them all day long!

The -c option will continue from the most recent logged message.

To continue a different chat, pass an integer ID to the --chat option. This should be the ID of a previously logged message. You can find these IDs using the llm logs command.

Thanks Amjith Ramanujam for contributing to this feature. #6

New mechanism for storing API keys#

API keys for language models such as those by OpenAI can now be saved using the new llm keys family of commands.

To set the default key to be used for the OpenAI APIs, run this:

llm keys set openai

Then paste in your API key.

Keys can also be passed using the new --key command line option - this can be a full key or the alias of a key that has been previously stored.

See API key management for more. #13

New location for the logs.db database#

The logs.db database that stores a history of executed prompts no longer lives at ~/.llm/log.db - it can now be found in a location that better fits the host operating system, which can be seen using:

llm logs path

On macOS this is ~/Library/Application Support/io.datasette.llm/logs.db.

To open that database using Datasette, run this:

datasette "$(llm logs path)"

You can upgrade your existing installation by copying your database to the new location like this:

cp ~/.llm/log.db "$(llm logs path)"
rm -rf ~/.llm # To tidy up the now obsolete directory

The database schema has changed, and will be updated automatically the first time you run the command.

That schema is included in the documentation. #35

Other changes#

New llm logs --truncate option (shortcut -t) which truncates the displayed prompts to make the log output easier to read. #16
Documentation now spans multiple pages and lives at https://llm.datasette.io/ #21
Default llm chatgpt command has been renamed to llm prompt. #17
Removed --code option in favour of new prompt templates mechanism. #24
Responses are now streamed by default, if the model supports streaming. The -s/--stream option has been removed. A new --no-stream option can be used to opt-out of streaming. #25
The -4/--gpt4 option has been removed in favour of -m 4 or -m gpt4, using a new mechanism that allows models to have additional short names.
The new gpt-3.5-turbo-16k model with a 16,000 token context length can now also be accessed using -m chatgpt-16k or -m 3.5-16k. Thanks, Benjamin Kirkbride. #37
Improved display of error messages from OpenAI. #15

0.3 (2023-05-17)#

llm logs command for browsing logs of previously executed completions. #3
llm "Python code to output factorial 10" --code option which sets a system prompt designed to encourage code to be output without any additional explanatory text. #5
Tool can now accept a prompt piped directly to standard input. #11

0.2 (2023-04-01)#

If a SQLite database exists in ~/.llm/log.db all prompts and responses are logged to that file. The llm init-db command can be used to create this file. #2

0.1 (2023-04-01)#

Initial prototype release. #1