Ability to create lexical graph only #127
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…into feature/lexical-graph-component
…into feature/lexical-graph-component # Conflicts: # docs/source/user_guide_kg_builder.rst # examples/pipeline/kg_builder_from_text.py
…into feature/lexical-graph-component
…into feature/lexical-graph-component # Conflicts: # examples/customize/build_graph/pipeline/lexical_graph_from_text.py
…into feature/lexical-graph-component
willtai
reviewed
Oct 22, 2024
Co-authored-by: willtai <wtaisen@gmail.com>
… into feature/lexical-graph-component
willtai
reviewed
Oct 22, 2024
| schema: Union[SchemaConfig, None] = None, | ||
| examples: str = "", | ||
| **kwargs: Any, | ||
| ) -> Neo4jGraph: | ||
| """Perform entity and relation extraction for all chunks in a list.""" | ||
| """Perform entity and relation extraction for all chunks in a list. |
There was a problem hiding this comment.
Could we define 'lexical graph' either here or in the user guide?
There was a problem hiding this comment.
This is what I tried to do here. What is missing? I'll add a note in this docstring anyway to clarify the behavior of create_lexical_graph and lexical_graph_config.
There was a problem hiding this comment.
Perhaps how is the term 'lexical graph' from any other knowledge graph. I think a newcomer will be confused with that
There was a problem hiding this comment.
Added more details and link to the user guide, let me know if you think more information is needd.
…into feature/lexical-graph-component
…ide when appropriate
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR adds a
LexicalGraphBuildercomponent that enables users to create the lexical graph without entity/relation extraction (see added example). It also updates theERExtractioncomponent to use the new LexicalGraphBuilder.Why
Pipelines that can be created after this PR:
A follow-up PR (#135) will implement the
Neo4jChunkReadercomponent that will enable to start the ER extraction from chunks already saved in the DB.Configuration
All parameters for the lexical graph are stored in a
LexicalGraphConfigobject (chunk and document node labels, relationship types, property names). This object is totally optional, default values are provided for all parameters.Future
We could consider deprecating the
create_lexical_graphbehavior in theEntityRelationExtractorand force users who want to build the lexical graph to use theLexicalGraphBuilder -> Neo4jWriterpattern.Type of Change
Complexity
Complexity: Medium
How Has This Been Tested?
Checklist
The following requirements should have been met (depending on the changes in the branch):