Populate docs/ from 0.7.1

Author: Automated

docs/changelog.md

@@ -1,5 +1,10 @@
 # Changelog
 
+(v0_7_1)=
+## 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](https://sqlite-utils.datasette.io/en/stable/changelog.html#v3-35). [#162](https://github.com/simonw/llm/issues/162)
+
 (v0_7)=
 ## 0.7 (2023-08-12)
 

docs/help.md

@@ -183,16 +183,12 @@ 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
-  -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.
+  -n, --count INTEGER  Number of entries to show - 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
+  --help               Show this message and exit.
 ```
 ### llm models --help
 ```
@@ -204,8 +200,8 @@ Options:
   --help  Show this message and exit.
 
 Commands:
-  list*    List available models
   default  Show or set the default model
+  list     List available models
 ```
 #### llm models list --help
 ```
@@ -236,10 +232,10 @@ 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
+  edit  Edit the specified prompt template using the default $EDITOR
+  list  List available prompt templates
+  path  Output the path to the templates directory
+  show  Show the specified prompt template
 ```
 #### llm templates list --help
 ```
@@ -287,7 +283,7 @@ Options:
   --help  Show this message and exit.
 
 Commands:
-  list*   List current aliases
+  list    List current aliases
   path    Output the path to the aliases.json file
   remove  Remove an alias
   set     Set an alias for a model

docs/logging.md

@@ -54,13 +54,7 @@ You can view the logs using the `llm logs` command:
 ```bash
 llm logs
 ```
-This will output the three most recent logged items in Markdown format
-
-Add `--json` to get the log messages in JSON instead:
-
-```bash
-llm logs --json
-```
+This will output the three most recent logged items as a JSON array of objects.
 
 Add `-n 10` to see the ten most recent items:
 ```bash
@@ -70,39 +64,19 @@ Or `-n 0` to see everything that has ever been logged:
 ```bash
 llm logs -n 0
 ```
-You can truncate the display of the prompts and responses using the `-t/--truncate` option. This can help make the JSON output more readable:
-```bash
-llm logs -n 5 -t --json
-```
-### Logs for a conversation
-
-To view the logs for the most recent {ref}`conversation <conversation>` you have had with a model, use `-c`:
-
-```bash
-llm logs -c
-```
-To see logs for a specific conversation based on its ID, use `--cid ID` or `--conversation ID`:
-
-```bash
-llm logs --cid 01h82n0q9crqtnzmf13gkyxawg
-```
-
-### Searching the logs
-
-You can search the logs for a search term in the `prompt` or the `response` columns.
+You can search the logs for a search term in the `prompt` or the `response` columns:
 ```bash
 llm logs -q 'cheesecake'
 ```
-The most relevant terms will be shown at the bottom of the output.
-
-### Filtering by model
-
 You can filter to logs just for a specific model (or model alias) using `-m/--model`:
 ```bash
 llm logs -m chatgpt
 ```
-
-### Browsing logs using Datasette
+You can truncate the display of the prompts and responses using the `-t/--truncate` option:
+```bash
+llm logs -n 5 -t
+```
+This is useful for finding a conversation that you would like to continue.
 
 You can also use [Datasette](https://datasette.io/) to browse your logs like this:
 

docs/other-models.md

@@ -12,7 +12,7 @@ To install **[llm-gpt4all](https://github.com/simonw/llm-gpt4all)**, providing 1
 ```bash
 llm install llm-gpt4all
 ```
-Run `llm models` to see the expanded list of available models.
+Run `llm models list` to see the expanded list of available models.
 
 To run a prompt through one of the models from GPT4All specify it using `-m/--model`:
 ```bash
@@ -52,9 +52,9 @@ With this configuration in place, the following command should run a prompt agai
 ```bash
 llm -m 0613 'What is the capital of France?'
 ```
-Run `llm models` to confirm that the new model is now available:
+Run `llm models list` to confirm that the new model is now available:
 ```bash
-llm models
+llm models list
 ```
 Example output:
 ```
@@ -87,7 +87,7 @@ If the `api_base` is set, the existing configured `openai` API key will not be s
 
 You can set `api_key_name` to the name of a key stored using the {ref}`api-keys` feature.
 
-Having configured the model like this, run `llm models` to check that it installed correctly. You can then run prompts against it like so:
+Having configured the model like this, run `llm models list` to check that it installed correctly. You can then run prompts against it like so:
 
 ```bash
 llm -m orca-openai-compat 'What is the capital of France?'
@@ -96,17 +96,3 @@ And confirm they were logged correctly with:
 ```bash
 llm logs -n 1
 ```
-
-### Extra HTTP headers
-
-Some providers such as [openrouter.ai](https://openrouter.ai/docs) may require the setting of additional HTTP headers. You can set those using the `headers:` key like this:
-
-```yaml
-- model_id: claude
-  model_name: anthropic/claude-2
-  api_base: "https://openrouter.ai/api/v1"
-  api_key_name: openrouter
-  headers:
-    HTTP-Referer: "https://llm.datasette.io/"
-    X-Title: LLM
-```

docs/plugins/installing-plugins.md

@@ -17,11 +17,11 @@ The `-y` flag skips asking for confirmation.
 
 You can see additional models that have been added by plugins by running:
 ```bash
-llm models
+llm models list
 ```
 Or add `--options` to include details of the options available for each model:
 ```bash
-llm models --options
+llm models list --options
 ```
 To run a prompt against a newly installed model, pass its name as the `-m/--model` option:
 ```bash

docs/plugins/tutorial-model-plugin.md

@@ -346,7 +346,7 @@ Let's add extra validation rules to our options. Length must be at least 2. Dura
 
 The `Options` class uses [Pydantic 2](https://pydantic.org/), which can support all sorts of advanced validation rules.
 
-We can also add inline documentation, which can then be displayed by the `llm models --options` command.
+We can also add inline documentation, which can then be displayed by the `llm models list --options` command.
 
 Add these imports to the top of `llm_markov.py`:
 ```python

docs/python-api.md

@@ -22,12 +22,10 @@ The `llm.get_model()` function accepts model names or aliases - so `chatgpt` wou
 Run this command to see a list of available models and their aliases:
 
 ```bash
-llm models
+llm models list
 ```
 If you have set a `OPENAI_API_KEY` environment variable you can omit the `model.key = ` line.
 
-Calling `llm.get_model()` with an invalid model name will raise a `llm.UnknownModelError` exception.
-
 (python-api-system-prompts)=
 
 ### System prompts
@@ -96,32 +94,3 @@ print(response2.text())
 You will get back five fun facts about skunks.
 
 Access `conversation.responses` for a list of all of the responses that have so far been returned during the conversation.
-
-## Other functions
-
-The `llm` top level package includes some useful utility functions.
-
-### set_alias(alias, model_id)
-
-The `llm.set_alias()` function can be used to define a new alias:
-
-```python
-import llm
-
-llm.set_alias("turbo", "gpt-3.5-turbo")
-```
-The second argument can be a model identifier or another alias, in which case that alias will be resolved.
-
-If the `aliases.json` file does not exist or contains invalid JSON it will be created or overwritten.
-
-### remove_alias(alias)
-
-Removes the alias with the given name from the `aliases.json` file.
-
-Raises `KeyError` if the alias does not exist.
-
-```python
-import llm
-
-llm.remove_alias("turbo")
-```

docs/requirements.txt

@@ -1,5 +1,4 @@
-sphinx==7.2.2
-furo==2023.8.17
+furo==2023.7.26
 sphinx-autobuild
 sphinx-copybutton
 myst-parser

docs/templates.md

@@ -26,6 +26,7 @@ You can also save default parameters:
 llm --system 'Summarize this text in the voice of $voice' \
   --model gpt-4 -p voice GlaDOS --save summarize
 ```
+
 ## Using a template
 
 You can execute a named template using the `-t/--template` option:
@@ -39,17 +40,6 @@ This can be combined with the `-m` option to specify a different model:
 curl -s https://llm.datasette.io/en/latest/ | \
   llm -t summarize -m gpt-3.5-turbo-16k
 ```
-## Listing available templates
-
-This command lists all available templates:
-```bash
-llm templates
-```
-The output looks something like this:
-```
-cmd        : system: reply with macos terminal commands only, no extra information
-glados     : system: You are GlaDOS prompt: Summarize this: $input
-```
 
 ## Templates as YAML files
 

docs/usage.md

@@ -30,7 +30,6 @@ Some models support options. You can pass these using `-o/--option name value` -
 llm 'Ten names for cheesecakes' -o temperature 1.5
 ```
 
-(conversation)=
 ## Continuing a conversation
 
 By default, the tool will start a new conversation each time you run it.
@@ -69,29 +68,12 @@ This is useful for piping content to standard input, for example:
 curl -s 'https://simonwillison.net/2023/May/15/per-interpreter-gils/' | \
   llm -s 'Suggest topics for this post as a JSON array'
 ```
-Different models support system prompts in different ways.
-
-The OpenAI models are particularly good at using system prompts as instructions for how they should process additional input sent as part of the regular prompt.
-
-Other models might use system prompts change the default voice and attitude of the model.
-
-System prompts can be saved as {ref}`templates <prompt-templates>` to create reusable tools. For example, you can create a template called `pytest` like this:
-
-```bash
-llm -s 'write pytest tests for this code' --save pytest
-```
-And then use the new template like this:
-```bash
-cat llm/utils.py | llm -t pytest
-```
-See {ref}`prompt templates <prompt-templates>` for more.
-
 ## Listing available models
 
-The `llm models` command lists every model that can be used with LLM, along with any aliases:
+The `llm models list` command lists every model that can be used with LLM, along with any aliases:
 
 ```bash
-llm models
+llm models list
 ```
 Example output:
 ```
@@ -103,7 +85,7 @@ PaLM 2: chat-bison-001 (aliases: palm, palm2)
 ```
 Add `--options` to also see documentation for the options supported by each model:
 ```bash
-llm models --options
+llm models list --options
 ```
 Output:
 <!-- [[[cog