diff --git a/website/docs/api/large-language-models.mdx b/website/docs/api/large-language-models.mdx index b9788ed8f..3fdd95939 100644 --- a/website/docs/api/large-language-models.mdx +++ b/website/docs/api/large-language-models.mdx @@ -113,7 +113,7 @@ note that this requirement will be included in the prompt, but the task doesn't perform a hard cut-off. It's hence possible that your summary exceeds `max_n_words`. -To perform [few-shot learning](/usage/large-langauge-models#few-shot-prompts), +To perform [few-shot learning](/usage/large-language-models#few-shot-prompts), you can write down a few examples in a separate file, and provide these to be injected into the prompt to the LLM. The default reader `spacy.FewShotReader.v1` supports `.yml`, `.yaml`, `.json` and `.jsonl`. @@ -192,7 +192,7 @@ the following parameters: span to the next token boundaries, e.g. expanding `"New Y"` out to `"New York"`. -To perform [few-shot learning](/usage/large-langauge-models#few-shot-prompts), +To perform [few-shot learning](/usage/large-language-models#few-shot-prompts), you can write down a few examples in a separate file, and provide these to be injected into the prompt to the LLM. The default reader `spacy.FewShotReader.v1` supports `.yml`, `.yaml`, `.json` and `.jsonl`. @@ -282,7 +282,7 @@ the following parameters: span to the next token boundaries, e.g. expanding `"New Y"` out to `"New York"`. -To perform [few-shot learning](/usage/large-langauge-models#few-shot-prompts), +To perform [few-shot learning](/usage/large-language-models#few-shot-prompts), you can write down a few examples in a separate file, and provide these to be injected into the prompt to the LLM. The default reader `spacy.FewShotReader.v1` supports `.yml`, `.yaml`, `.json` and `.jsonl`. @@ -397,7 +397,7 @@ definitions are included in the prompt. | `allow_none` | When set to `True`, allows the LLM to not return any of the given label. The resulting dict in `doc.cats` will have `0.0` scores for all labels. Defaults to `True`. ~~bool~~ | | `verbose` | If set to `True`, warnings will be generated when the LLM returns invalid responses. Defaults to `False`. ~~bool~~ | -To perform [few-shot learning](/usage/large-langauge-models#few-shot-prompts), +To perform [few-shot learning](/usage/large-language-models#few-shot-prompts), you can write down a few examples in a separate file, and provide these to be injected into the prompt to the LLM. The default reader `spacy.FewShotReader.v1` supports `.yml`, `.yaml`, `.json` and `.jsonl`. @@ -452,7 +452,7 @@ prompting and includes an improved prompt template. | `allow_none` | When set to `True`, allows the LLM to not return any of the given label. The resulting dict in `doc.cats` will have `0.0` scores for all labels. Defaults to `True`. ~~bool~~ | | `verbose` | If set to `True`, warnings will be generated when the LLM returns invalid responses. Defaults to `False`. ~~bool~~ | -To perform [few-shot learning](/usage/large-langauge-models#few-shot-prompts), +To perform [few-shot learning](/usage/large-language-models#few-shot-prompts), you can write down a few examples in a separate file, and provide these to be injected into the prompt to the LLM. The default reader `spacy.FewShotReader.v1` supports `.yml`, `.yaml`, `.json` and `.jsonl`. @@ -502,7 +502,7 @@ prompting. | `allow_none` | When set to `True`, allows the LLM to not return any of the given label. The resulting dict in `doc.cats` will have `0.0` scores for all labels. Deafults to `True`. ~~bool~~ | | `verbose` | If set to `True`, warnings will be generated when the LLM returns invalid responses. Deafults to `False`. ~~bool~~ | -To perform [few-shot learning](/usage/large-langauge-models#few-shot-prompts), +To perform [few-shot learning](/usage/large-language-models#few-shot-prompts), you can write down a few examples in a separate file, and provide these to be injected into the prompt to the LLM. The default reader `spacy.FewShotReader.v1` supports `.yml`, `.yaml`, `.json` and `.jsonl`. @@ -546,12 +546,12 @@ on an upstream NER component for entities extraction. | ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `labels` | List of labels or str of comma-separated list of labels. ~~Union[List[str], str]~~ | | `template` | Custom prompt template to send to LLM model. Default templates for each task are located in the `spacy_llm/tasks/templates` directory. Defaults to [`rel.jinja`](https://github.com/explosion/spacy-llm/blob/main/spacy_llm/tasks/templates/rel.jinja). ~~str~~ | -| `label_description` | Dictionary providing a description for each relation label. Defaults to `None`. ~~Optional[Dict[str, str]]~~ | +| `label_definitions` | Dictionary providing a description for each relation label. Defaults to `None`. ~~Optional[Dict[str, str]]~~ | | `examples` | Optional function that generates examples for few-shot learning. Defaults to `None`. ~~Optional[Callable[[], Iterable[Any]]]~~ | | `normalizer` | Function that normalizes the labels as returned by the LLM. If `None`, falls back to `spacy.LowercaseNormalizer.v1`. Defaults to `None`. ~~Optional[Callable[[str], str]]~~ | | `verbose` | If set to `True`, warnings will be generated when the LLM returns invalid responses. Defaults to `False`. ~~bool~~ | -To perform [few-shot learning](/usage/large-langauge-models#few-shot-prompts), +To perform [few-shot learning](/usage/large-language-models#few-shot-prompts), you can write down a few examples in a separate file, and provide these to be injected into the prompt to the LLM. The default reader `spacy.FewShotReader.v1` supports `.yml`, `.yaml`, `.json` and `.jsonl`. @@ -565,6 +565,7 @@ supports `.yml`, `.yaml`, `.json` and `.jsonl`. [components.llm.task] @llm_tasks = "spacy.REL.v1" labels = ["LivesIn", "Visits"] + [components.llm.task.examples] @misc = "spacy.FewShotReader.v1" path = "rel_examples.jsonl" @@ -613,7 +614,7 @@ doesn't match the number of tokens from the pipeline's tokenizer, no lemmas are stored in the corresponding doc's tokens. Otherwise the tokens `.lemma_` property is updated with the lemma suggested by the LLM. -To perform [few-shot learning](/usage/large-langauge-models#few-shot-prompts), +To perform [few-shot learning](/usage/large-language-models#few-shot-prompts), you can write down a few examples in a separate file, and provide these to be injected into the prompt to the LLM. The default reader `spacy.FewShotReader.v1` supports `.yml`, `.yaml`, `.json` and `.jsonl`. @@ -666,7 +667,7 @@ issues (e. g. in case of unexpected LLM responses) the value might be `None`. | `examples` | Optional function that generates examples for few-shot learning. Defaults to `None`. ~~Optional[Callable[[], Iterable[Any]]]~~ | | `field` | Name of extension attribute to store summary in (i. e. the summary will be available in `doc._.{field}`). Defaults to `sentiment`. ~~str~~ | -To perform [few-shot learning](/usage/large-langauge-models#few-shot-prompts), +To perform [few-shot learning](/usage/large-language-models#few-shot-prompts), you can write down a few examples in a separate file, and provide these to be injected into the prompt to the LLM. The default reader `spacy.FewShotReader.v1` supports `.yml`, `.yaml`, `.json` and `.jsonl`.