Move LLM_RAISE_ERRORS to advanced model plugins, closes #1121

README.md

@@ -237,7 +237,6 @@ See also [the llm tag](https://simonwillison.net/tags/llm/) on my blog.
     * [SQL schema](https://llm.datasette.io/en/stable/embeddings/python-api.html#sql-schema)
   * [Writing plugins to add new embedding models](https://llm.datasette.io/en/stable/embeddings/writing-plugins.html)
     * [Embedding binary content](https://llm.datasette.io/en/stable/embeddings/writing-plugins.html#embedding-binary-content)
-    * [LLM_RAISE_ERRORS](https://llm.datasette.io/en/stable/embeddings/writing-plugins.html#llm-raise-errors)
   * [Embedding storage format](https://llm.datasette.io/en/stable/embeddings/storage.html)
 * [Plugins](https://llm.datasette.io/en/stable/plugins/index.html)
   * [Installing plugins](https://llm.datasette.io/en/stable/plugins/installing-plugins.html)
@@ -281,6 +280,7 @@ See also [the llm tag](https://simonwillison.net/tags/llm/) on my blog.
     * [Attachments for multi-modal models](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#attachments-for-multi-modal-models)
     * [Tracking token usage](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#tracking-token-usage)
     * [Tracking resolved model names](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#tracking-resolved-model-names)
+    * [LLM_RAISE_ERRORS](https://llm.datasette.io/en/stable/plugins/advanced-model-plugins.html#llm-raise-errors)
   * [Utility functions for plugins](https://llm.datasette.io/en/stable/plugins/plugin-utilities.html)
     * [llm.get_key()](https://llm.datasette.io/en/stable/plugins/plugin-utilities.html#llm-get-key)
     * [llm.user_dir()](https://llm.datasette.io/en/stable/plugins/plugin-utilities.html#llm-user-dir)

docs/embeddings/writing-plugins.md

@@ -66,18 +66,3 @@ class ClipEmbeddingModel(llm.EmbeddingModel):
 If your model accepts binary, your `.embed_batch()` model may be called with a list of Python bytestrings. These may be mixed with regular strings if the model accepts both types of input.
 
 [llm-clip](https://github.com/simonw/llm-clip) is an example of a model that can embed both binary and text content.
-
-## LLM_RAISE_ERRORS
-
-While working on a plugin it can be useful to request that errors are raised instead of being caught and logged, so you can access them from the Python debugger.
-
-Set the `LLM_RAISE_ERRORS` environment variable to enable this behavior, then run `llm` like this:
-
-```bash
-LLM_RAISE_ERRORS=1 python -i -m llm ...
-```
-The `-i` option means Python will drop into an interactive shell if an error occurs. You can then open a debugger at the most recent error using:
-
-```python
-import pdb; pdb.pm()
-```

docs/plugins/advanced-model-plugins.md

@@ -290,4 +290,21 @@ If those APIs return the _real_ model ID that was used, your plugin can record t
 ```bash
 response.set_resolved_model(resolved_model_id)
 ```
-This string will be recorded in the database and shown in the output of `llm logs` and `llm logs --json`.
+This string will be recorded in the database and shown in the output of `llm logs` and `llm logs --json`.
+
+(tutorial-model-plugin-raise-errors)=
+
+## LLM_RAISE_ERRORS
+
+While working on a plugin it can be useful to request that errors are raised instead of being caught and logged, so you can access them from the Python debugger.
+
+Set the `LLM_RAISE_ERRORS` environment variable to enable this behavior, then run `llm` like this:
+
+```bash
+LLM_RAISE_ERRORS=1 python -i -m llm ...
+```
+The `-i` option means Python will drop into an interactive shell if an error occurs. You can then open a debugger at the most recent error using:
+
+```python
+import pdb; pdb.pm()
+```