Llm

- 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](https://github.com/simonw/llm/issues/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 {ref}`system prompts <system-prompts>`. [153](https://github.com/simonw/llm/issues/153)
- Additional {ref}`openai-compatible-models` can now be configured with custom HTTP headers. This enables platforms such as [openrouter.ai](https://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](https://github.com/simonw/llm/issues/158)
- The documentation now includes a {ref}`plugin directory <plugin-directory>` listing all available plugins for LLM. [173](https://github.com/simonw/llm/issues/173)
- New {ref}`related tools <related-tools>` section in the documentation describing `ttok`, `strip-tags` and `symbex`. [111](https://github.com/simonw/llm/issues/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](https://github.com/simonw/llm/issues/167)
- New `llm keys` (aka `llm keys list`) command for listing the names of all configured keys. [174](https://github.com/simonw/llm/issues/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](https://github.com/simonw/llm/pull/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](https://github.com/cmungall). [#147](https://github.com/simonw/llm/pull/147)
- `llm.get_model(model_id)` is now documented as raising `llm.UnknownModelError` if the requested model does not exist. [155](https://github.com/simonw/llm/issues/155)

(v0_7_1)=

- 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](https://sqlite-utils.datasette.io/en/stable/changelog.html#v3-35). [162](https://github.com/simonw/llm/issues/162)

(v0_7)=

The new {ref}`aliases` commands can be used to configure additional aliases for models, for example:

bash
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:

bash
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](https://github.com/simonw/llm/issues/151)

Notable new plugins

- **[llm-mlc](https://github.com/simonw/llm-mlc)** can run local models released by the [MLC project](https://mlc.ai/mlc-llm/), including models that can take advantage of the GPU on Apple Silicon M1/M2 devices.
- **[llm-llama-cpp](https://github.com/simonw/llm-llama-cpp)** uses [llama.cpp](https://github.com/ggerganov/llama.cpp) to run models published in the GGML format. See [Run Llama 2 on your own Mac using LLM and Homebrew](https://simonwillison.net/2023/Aug/1/llama-2-mac/) for more details.

Also in this release

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

(v0_6_1)=

- LLM can now be installed directly from Homebrew core: `brew install llm`. [124](https://github.com/simonw/llm/issues/124)
- Python API documentation now covers {ref}`python-api-system-prompts`.
- Fixed incorrect example in the {ref}`prompt-templates` documentation. Thanks, Jorge Cabello. [125](https://github.com/simonw/llm/pull/125)

(v0_6)=

- Models hosted on [Replicate](https://replicate.com/) can now be accessed using the [llm-replicate](https://github.com/simonw/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](https://simonwillison.net/2023/Jul/18/accessing-llama-2/).
- Model providers that expose an API that is compatible with the OpenAPI API format, including self-hosted model servers such as [LocalAI](https://github.com/go-skynet/LocalAI), can now be accessed using {ref}`additional configuration <openai-compatible-models>` for the default OpenAI plugin. [#106](https://github.com/simonw/llm/issues/106)
- OpenAI models that are not yet supported by LLM can also {ref}`be configured <openai-extra-models>` using the new `extra-openai-models.yaml` configuration file. [107](https://github.com/simonw/llm/issues/107)
- The {ref}`llm logs command <viewing-logs>` 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](https://github.com/simonw/llm/issues/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](https://github.com/simonw/llm/issues/109)

(v0_5)=

LLM now supports **additional language models**, thanks to a new {ref}`plugins mechanism <installing-plugins>` for installing additional models.

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

- [llm-gpt4all](https://github.com/simonw/llm-gpt4all) adds support for 17 models that can download and run on your own device, including Vicuna, Falcon and wizardLM.
- [llm-mpt30b](https://github.com/simonw/llm-mpt30b) adds support for the MPT-30B model, a 19GB download.
- [llm-palm](https://github.com/simonw/llm-palm) adds support for Google's PaLM 2 via the Google API.

A comprehensive tutorial, {ref}`writing a plugin to support a new model <tutorial-model-plugin>` describes how to add new models by building plugins in detail.

New features

- {ref}`python-api` documentation for using LLM models, including models from plugins, directly from Python. [75](https://github.com/simonw/llm/issues/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](https://github.com/simonw/llm/issues/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](https://github.com/simonw/llm/issues/91)
- New `-o/--option name value` syntax for setting options for models, such as temperature. Available options differ for different models. [63](https://github.com/simonw/llm/issues/63)
- `llm models list --options` command for viewing all available model options. [82](https://github.com/simonw/llm/issues/82)
- `llm "prompt" --save template` option for saving a prompt directly to a template. [55](https://github.com/simonw/llm/issues/55)
- Prompt templates can now specify {ref}`default values <prompt-default-parameters>` for parameters. Thanks, Chris Mungall. [57](https://github.com/simonw/llm/pull/57)
- `llm openai models` command to list all available OpenAI models from their API. [70](https://github.com/simonw/llm/issues/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](https://github.com/simonw/llm/issues/31)

Smaller improvements

- `llm -s` is now a shortcut for `llm --system`. [69](https://github.com/simonw/llm/issues/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](https://github.com/simonw/llm/issues/76)
- Documentation covering {ref}`plugin-utilities`.
- Documentation site now uses Plausible for analytics. [79](https://github.com/simonw/llm/issues/79)

(v0_4_1)=