explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-12 18:26:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix LLM docs on task factories.

Browse Source
This commit is contained in:
Raphael Mitsch 2024-01-19 16:48:54 +01:00
parent 256468c414
commit 575c405ae3
1 changed files with 5 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
website/docs/api/large-language-models.mdx
View File

@ -20,10 +20,9 @@ An LLM component is implemented through the `LLMWrapper` class. It is accessible
through a generic `llm`
[component factory](https://spacy.io/usage/processing-pipelines#custom-components-factories)
as well as through task-specific component factories: `llm_ner`, `llm_spancat`,
`llm_rel`, `llm_textcat`, `llm_sentiment`, `llm_summarization` and
`llm_entity_linker`.
### LLMWrapper.\_\_init\_\_ {id="init",tag="method"}
`llm_rel`, `llm_textcat`, `llm_sentiment`, `llm_summarization`,
`llm_entity_linker`, `llm_raw` and `llm_translation`. For these factories, the
GPT-3-5 model from OpenAI is used by default, but this can be customized.
> #### Example
>
@ -43,14 +42,6 @@ as well as through task-specific component factories: `llm_ner`, `llm_spancat`,
> llm = LLMWrapper(vocab=nlp.vocab, task=task, model=model, cache=cache, save_io=True)
> ```
An LLM component is implemented through the `LLMWrapper` class. It is accessible
through a generic `llm`
[component factory](https://spacy.io/usage/processing-pipelines#custom-components-factories)
as well as through task-specific component factories: `llm_ner`, `llm_spancat`,
`llm_rel`, `llm_textcat`, `llm_sentiment` and `llm_summarization`. For these
factories, the GPT-3-5 model from OpenAI is used by default, but this can be
customized.
### LLMWrapper.\_\_init\_\_ {id="init",tag="method"}
Create a new pipeline instance. In your application, you would normally use a
@ -238,8 +229,8 @@ All tasks are registered in the `llm_tasks` registry.
dataset across multiple storage units for easier processing and lookups. In
`spacy-llm` we use this term (synonymously: "mapping") to describe the splitting
up of prompts if they are too long for a model to handle, and "fusing"
(synonymously: "reducing") to describe how the model responses for several shards
are merged back together into a single document.
(synonymously: "reducing") to describe how the model responses for several
shards are merged back together into a single document.
Prompts are broken up in a manner that _always_ keeps the prompt in the template
intact, meaning that the instructions to the LLM will always stay complete. The