explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-27 08:29:51 +03:00
Code Issues Packages Projects Releases Wiki Activity

Apply suggestions from code review

Browse Source 
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
This commit is contained in:
Raphael Mitsch 2023-11-29 10:04:06 +01:00 committed by GitHub
parent d48ae4405c
commit 4c14ac9e71
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
website/docs/api/large-language-models.mdx
View File

@ -306,7 +306,7 @@ path = "summarization_examples.yml"
### EL (Entity Linking) {id="nel"} ### EL (Entity Linking) {id="nel"}
The EL links recognized entities (see [NER](#ner)) to those in a knowledge base The EL links recognized entities (see [NER](#ner)) to those in a knowledge base
(KB). The EL task prompts the LLM to select the most likely candidates from the (KB). The EL task prompts the LLM to select the most likely candidate from the
KB, whose structure can be arbitrary. KB, whose structure can be arbitrary.
Note that the documents processed by the entity linking task are expected to Note that the documents processed by the entity linking task are expected to
@ -322,7 +322,7 @@ fetch descriptions for any given entity ID. Descriptions can be empty, but
ideally provide more context for entities stored in the KB. ideally provide more context for entities stored in the KB.
`spacy-llm` provides a `CandidateSelector` implementation `spacy-llm` provides a `CandidateSelector` implementation
(`spacy.CandidateSelector.v1`) that leverages a a spaCy knowledge base -as used (`spacy.CandidateSelector.v1`) that leverages a spaCy knowledge base -as used
in an `entity_linking` component - to select candidates. This knowledge base can in an `entity_linking` component - to select candidates. This knowledge base can
be loaded from an existing spaCy pipeline (note that the pipeline's EL component be loaded from an existing spaCy pipeline (note that the pipeline's EL component
doesn't have to be trained) or from a separate .yaml file. doesn't have to be trained) or from a separate .yaml file.
@ -432,7 +432,7 @@ format:
```yaml ```yaml
entities: entities:
# The key should be whatever ID identifies this entity in your knowledge base. # The key should be whatever ID identifies this entity uniquely in your knowledge base.
ID1: ID1:
name: "..." name: "..."
desc: "..." desc: "..."
@ -459,7 +459,7 @@ for a toy example of how such a KB file might look like.
> >
> ```ini > ```ini
> [initialize.components.llm.candidate_selector.kb_loader] > [initialize.components.llm.candidate_selector.kb_loader]
> @llm_misc = "spacy.KBObjectLoader.v1" > @llm_misc = "spacy.KBFileLoader.v1"
> # Path to knowledge base file. > # Path to knowledge base file.
> path = ${paths.el_kb} > path = ${paths.el_kb}
> ``` > ```