From c13f9ec933fc028f29dff2ed190d4cd99ba2c7a5 Mon Sep 17 00:00:00 2001 From: svlandeg Date: Fri, 1 Sep 2023 12:07:48 +0200 Subject: [PATCH] v3 overview of parameters --- website/docs/api/large-language-models.mdx | 164 +++++++++++++-------- 1 file changed, 100 insertions(+), 64 deletions(-) diff --git a/website/docs/api/large-language-models.mdx b/website/docs/api/large-language-models.mdx index 9ad56dd83..70d3548b2 100644 --- a/website/docs/api/large-language-models.mdx +++ b/website/docs/api/large-language-models.mdx @@ -107,12 +107,12 @@ prompting. > max_n_words = null > ``` -| Argument | Description | -| ------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `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 [summarization.v1.jinja](https://github.com/explosion/spacy-llm/blob/main/spacy_llm/tasks/templates/summarization.v1.jinja). ~~str~~ | -| `examples` | Optional function that generates examples for few-shot learning. Defaults to `None`. ~~Optional[Callable[[], Iterable[Any]]]~~ | -| `max_n_words` | Maximum number of words to be used in summary. Note that this should not expected to work exactly. Defaults to `None`. ~~Optional[int]~~ | -| `field` | Name of extension attribute to store summary in (i. e. the summary will be available in `doc._.{field}`). Defaults to `summary`. ~~str~~ | +| Argument | Description | +| ------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `template` | Custom prompt template to send to LLM model. Defaults to [summarization.v1.jinja](https://github.com/explosion/spacy-llm/blob/main/spacy_llm/tasks/templates/summarization.v1.jinja). ~~str~~ | +| `examples` | Optional function that generates examples for few-shot learning. Defaults to `None`. ~~Optional[Callable[[], Iterable[Any]]]~~ | +| `max_n_words` | Maximum number of words to be used in summary. Note that this should not expected to work exactly. Defaults to `None`. ~~Optional[int]~~ | +| `field` | Name of extension attribute to store summary in (i. e. the summary will be available in `doc._.{field}`). Defaults to `summary`. ~~str~~ | The summarization task prompts the model for a concise summary of the provided text. It optionally allows to limit the response to a certain number of tokens - @@ -157,6 +157,40 @@ path = "summarization_examples.yml" The NER task identifies non-overlapping entities in text. +#### spacy.NER.v3 {id="ner-v3"} + +Version 3 is fundamentally different to v1 and v2, as it implements +Chain-of-Thought prompting, based on +[the PromptNER paper by Ashok and Lipton (2023)](https://arxiv.org/pdf/2305.15444.pdf). +From preliminary experiments, we've found this implementation to obtain +significant better accuracy. + +> #### Example config +> +> ```ini +> [components.llm.task] +> @llm_tasks = "spacy.NER.v3" +> labels = ["PERSON", "ORGANISATION", "LOCATION"] +> ``` + +When no examples are [specified](/usage/large-language-models#few-shot-prompts), +the v3 implementation will use a dummy example in the prompt. Technically this +means that the task will always perform few-shot prompting under the hood. + +| Argument | Description | +| ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | +| `labels` | List of labels or str of comma-separated list of labels. ~~Union[List[str], str]~~ | +| `label_definitions` | Optional dict mapping a label to a description of that label. These descriptions are added to the prompt to help instruct the LLM on what to extract. Defaults to `None`. ~~Optional[Dict[str, str]]~~ | +| `template` | Custom prompt template to send to LLM model. Defaults to [ner.v3.jinja](https://github.com/explosion/spacy-llm/blob/main/spacy_llm/tasks/templates/ner.v3.jinja). ~~str~~ | +| `description` (NEW) | A description of what to recognize or not recognize as entities. ~~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`, defaults to `spacy.LowercaseNormalizer.v1`. Defaults to `None`. ~~Optional[Callable[[str], str]]~~ | +| `alignment_mode` | Alignment mode in case the LLM returns entities that do not align with token boundaries. Options are `"strict"`, `"contract"` or `"expand"`. Defaults to `"contract"`. ~~str~~ | +| `case_sensitive_matching` | Whether to search without case sensitivity. Defaults to `False`. ~~bool~~ | + +Note that the `single_match` parameter, used in v1 and v2, is not supported +anymore, as the CoT parsing takes care of this automatically. + #### spacy.NER.v2 {id="ner-v2"} This version supports explicitly defining the provided labels with custom @@ -172,16 +206,16 @@ v1. > examples = null > ``` -| Argument | Description | -| ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `labels` | List of labels or str of comma-separated list of labels. ~~Union[List[str], str]~~ | -| `template` (NEW) | Custom prompt template to send to LLM model. Default templates for each task are located in the `spacy_llm/tasks/templates` directory. Defaults to [ner.v2.jinja](https://github.com/explosion/spacy-llm/blob/main/spacy_llm/tasks/templates/ner.v2.jinja). ~~str~~ | -| `label_definitions` (NEW) | Optional dict mapping a label to a description of that label. These descriptions are added to the prompt to help instruct the LLM on what to extract. 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`, defaults to `spacy.LowercaseNormalizer.v1`. Defaults to `None`. ~~Optional[Callable[[str], str]]~~ | -| `alignment_mode` | Alignment mode in case the LLM returns entities that do not align with token boundaries. Options are `"strict"`, `"contract"` or `"expand"`. Defaults to `"contract"`. ~~str~~ | -| `case_sensitive_matching` | Whether to search without case sensitivity. Defaults to `False`. ~~bool~~ | -| `single_match` | Whether to match an entity in the LLM's response only once (the first hit) or multiple times. Defaults to `False`. ~~bool~~ | +| Argument | Description | +| ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | +| `labels` | List of labels or str of comma-separated list of labels. ~~Union[List[str], str]~~ | +| `label_definitions` (NEW) | Optional dict mapping a label to a description of that label. These descriptions are added to the prompt to help instruct the LLM on what to extract. Defaults to `None`. ~~Optional[Dict[str, str]]~~ | +| `template` (NEW) | Custom prompt template to send to LLM model. Defaults to [ner.v2.jinja](https://github.com/explosion/spacy-llm/blob/main/spacy_llm/tasks/templates/ner.v2.jinja). ~~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`, defaults to `spacy.LowercaseNormalizer.v1`. Defaults to `None`. ~~Optional[Callable[[str], str]]~~ | +| `alignment_mode` | Alignment mode in case the LLM returns entities that do not align with token boundaries. Options are `"strict"`, `"contract"` or `"expand"`. Defaults to `"contract"`. ~~str~~ | +| `case_sensitive_matching` | Whether to search without case sensitivity. Defaults to `False`. ~~bool~~ | +| `single_match` | Whether to match an entity in the LLM's response only once (the first hit) or multiple times. Defaults to `False`. ~~bool~~ | The parameters `alignment_mode`, `case_sensitive_matching` and `single_match` are identical to the [v1](#ner-v1) implementation. The format of few-shot @@ -292,17 +326,17 @@ support overlapping entities and store its annotations in `doc.spans`. > examples = null > ``` -| Argument | Description | -| ------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `labels` | List of labels or str of comma-separated list of labels. ~~Union[List[str], str]~~ | -| `template` (NEW) | Custom prompt template to send to LLM model. Default templates for each task are located in the `spacy_llm/tasks/templates` directory. Defaults to [`spancat.v2.jinja`](https://github.com/explosion/spacy-llm/blob/main/spacy_llm/tasks/templates/spancat.v2.jinja). ~~str~~ | -| `label_definitions` (NEW) | Optional dict mapping a label to a description of that label. These descriptions are added to the prompt to help instruct the LLM on what to extract. Defaults to `None`. ~~Optional[Dict[str, str]]~~ | -| `spans_key` | Key of the `Doc.spans` dict to save the spans under. Defaults to `"sc"`. ~~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`, defaults to `spacy.LowercaseNormalizer.v1`. ~~Optional[Callable[[str], str]]~~ | -| `alignment_mode` | Alignment mode in case the LLM returns entities that do not align with token boundaries. Options are `"strict"`, `"contract"` or `"expand"`. Defaults to `"contract"`. ~~str~~ | -| `case_sensitive_matching` | Whether to search without case sensitivity. Defaults to `False`. ~~bool~~ | -| `single_match` | Whether to match an entity in the LLM's response only once (the first hit) or multiple times. Defaults to `False`. ~~bool~~ | +| Argument | Description | +| ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | +| `labels` | List of labels or str of comma-separated list of labels. ~~Union[List[str], str]~~ | +| `template` (NEW) | Custom prompt template to send to LLM model. Defaults to [`spancat.v2.jinja`](https://github.com/explosion/spacy-llm/blob/main/spacy_llm/tasks/templates/spancat.v2.jinja). ~~str~~ | +| `label_definitions` (NEW) | Optional dict mapping a label to a description of that label. These descriptions are added to the prompt to help instruct the LLM on what to extract. Defaults to `None`. ~~Optional[Dict[str, str]]~~ | +| `spans_key` | Key of the `Doc.spans` dict to save the spans under. Defaults to `"sc"`. ~~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`, defaults to `spacy.LowercaseNormalizer.v1`. ~~Optional[Callable[[str], str]]~~ | +| `alignment_mode` | Alignment mode in case the LLM returns entities that do not align with token boundaries. Options are `"strict"`, `"contract"` or `"expand"`. Defaults to `"contract"`. ~~str~~ | +| `case_sensitive_matching` | Whether to search without case sensitivity. Defaults to `False`. ~~bool~~ | +| `single_match` | Whether to match an entity in the LLM's response only once (the first hit) or multiple times. Defaults to `False`. ~~bool~~ | Except for the `spans_key` parameter, the SpanCat v2 task reuses the configuration from the NER v2 task. Refer to [its documentation](#ner-v2) for @@ -360,16 +394,16 @@ prompt. > examples = null > ``` -| Argument | Description | -| ------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `labels` | List of labels or str of comma-separated list of labels. ~~Union[List[str], str]~~ | -| `label_definitions` (NEW) | Dictionary of label definitions. Included in the prompt, if set. Defaults to `None`. ~~Optional[Dict[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 [`textcat.v3.jinja`](https://github.com/explosion/spacy-llm/blob/main/spacy_llm/tasks/templates/textcat.v3.jinja). ~~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]]~~ | -| `exclusive_classes` | If set to `True`, only one label per document should be valid. If set to `False`, one document can have multiple labels. Defaults to `False`. ~~bool~~ | -| `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~~ | +| Argument | Description | +| ------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `labels` | List of labels or str of comma-separated list of labels. ~~Union[List[str], str]~~ | +| `label_definitions` (NEW) | Dictionary of label definitions. Included in the prompt, if set. Defaults to `None`. ~~Optional[Dict[str, str]]~~ | +| `template` | Custom prompt template to send to LLM model. Defaults to [`textcat.v3.jinja`](https://github.com/explosion/spacy-llm/blob/main/spacy_llm/tasks/templates/textcat.v3.jinja). ~~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]]~~ | +| `exclusive_classes` | If set to `True`, only one label per document should be valid. If set to `False`, one document can have multiple labels. Defaults to `False`. ~~bool~~ | +| `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~~ | The formatting of few-shot examples is the same as those for the [v1](#textcat-v1) implementation. @@ -387,15 +421,15 @@ V2 includes all v1 functionality, with an improved prompt template. > examples = null > ``` -| Argument | Description | -| ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `labels` | List of labels or str of comma-separated list of labels. ~~Union[List[str], str]~~ | -| `template` (NEW) | Custom prompt template to send to LLM model. Default templates for each task are located in the `spacy_llm/tasks/templates` directory. Defaults to [`textcat.v2.jinja`](https://github.com/explosion/spacy-llm/blob/main/spacy_llm/tasks/templates/textcat.v2.jinja). ~~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`. ~~Optional[Callable[[str], str]]~~ | -| `exclusive_classes` | If set to `True`, only one label per document should be valid. If set to `False`, one document can have multiple labels. Defaults to `False`. ~~bool~~ | -| `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~~ | +| Argument | Description | +| ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `labels` | List of labels or str of comma-separated list of labels. ~~Union[List[str], str]~~ | +| `template` (NEW) | Custom prompt template to send to LLM model. Defaults to [`textcat.v2.jinja`](https://github.com/explosion/spacy-llm/blob/main/spacy_llm/tasks/templates/textcat.v2.jinja). ~~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`. ~~Optional[Callable[[str], str]]~~ | +| `exclusive_classes` | If set to `True`, only one label per document should be valid. If set to `False`, one document can have multiple labels. Defaults to `False`. ~~bool~~ | +| `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~~ | The formatting of few-shot examples is the same as those for the [v1](#textcat-v1) implementation. @@ -464,14 +498,14 @@ on an upstream NER component for entities extraction. > labels = ["LivesIn", "Visits"] > ``` -| Argument | Description | -| ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `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.v1.jinja`](https://github.com/explosion/spacy-llm/blob/main/spacy_llm/tasks/templates/rel.v1.jinja). ~~str~~ | -| `label_description` | 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~~ | +| Argument | Description | +| ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `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. Defaults to [`rel.v3.jinja`](https://github.com/explosion/spacy-llm/blob/main/spacy_llm/tasks/templates/rel.v1.jinja). ~~str~~ | +| `label_description` | 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-language-models#few-shot-prompts), you can write down a few examples in a separate file, and provide these to be @@ -513,10 +547,10 @@ This task supports both zero-shot and few-shot prompting. > examples = null > ``` -| Argument | Description | -| ---------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `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 [lemma.v1.jinja](https://github.com/explosion/spacy-llm/blob/main/spacy_llm/tasks/templates/lemma.v1.jinja). ~~str~~ | -| `examples` | Optional function that generates examples for few-shot learning. Defaults to `None`. ~~Optional[Callable[[], Iterable[Any]]]~~ | +| Argument | Description | +| ---------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `template` | Custom prompt template to send to LLM model. Defaults to [lemma.v1.jinja](https://github.com/explosion/spacy-llm/blob/main/spacy_llm/tasks/templates/lemma.v1.jinja). ~~str~~ | +| `examples` | Optional function that generates examples for few-shot learning. Defaults to `None`. ~~Optional[Callable[[], Iterable[Any]]]~~ | The task prompts the LLM to lemmatize the passed text and return the lemmatized version as a list of tokens and their corresponding lemma. E. g. the text @@ -590,11 +624,11 @@ This task supports both zero-shot and few-shot prompting. > examples = null > ``` -| Argument | Description | -| ---------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `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 [sentiment.v1.jinja](./spacy_llm/tasks/templates/sentiment.v1.jinja). ~~str~~ | -| `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~~ | +| Argument | Description | +| ---------- | ------------------------------------------------------------------------------------------------------------------------------------------ | +| `template` | Custom prompt template to send to LLM model. Defaults to [sentiment.v1.jinja](./spacy_llm/tasks/templates/sentiment.v1.jinja). ~~str~~ | +| `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-language-models#few-shot-prompts), you can write down a few examples in a separate file, and provide these to be @@ -648,7 +682,9 @@ implementations can have other signatures, like ### Models via REST API {id="models-rest"} -These models all take the same parameters, but note that the `config` should contain provider-specific keys and values, as it will be passed onwards to the provider's API. +These models all take the same parameters, but note that the `config` should +contain provider-specific keys and values, as it will be passed onwards to the +provider's API. | Argument | Description | | ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------- |