feat(llm): support multiple property_type & importing graph from the entire doc#84
Merged
imbajin merged 14 commits intoapache:mainfrom Oct 10, 2024
Merged
feat(llm): support multiple property_type & importing graph from the entire doc#84imbajin merged 14 commits intoapache:mainfrom
imbajin merged 14 commits intoapache:mainfrom
Conversation
dosubot
bot
added
the
size:L
dosubot
bot
added
bug
10 tasks
vichayturen
changed the title
dosubot
bot
added
size:XL
imbajin
reviewed
Oct 9, 2024
hugegraph-llm/src/hugegraph_llm/operators/hugegraph_op/schema_manager.py
Outdated
Show resolved
Hide resolved
simon824
reviewed
Oct 9, 2024
| for prop in properties: | ||
| self.schema.propertyKey(prop).asText().ifNotExist().create() | ||
| # for prop in properties: | ||
| # self.schema.propertyKey(prop).asText().ifNotExist().create() |
| for prop in properties: | ||
| self.schema.propertyKey(prop).asText().ifNotExist().create() | ||
| # for prop in properties: | ||
| # self.schema.propertyKey(prop).asText().ifNotExist().create() |
| language: Literal["zh", "en"] = "zh" | ||
| self, | ||
| text: Union[str, List[str]], # text to be split | ||
| split_type: Literal["document", "paragraph", "sentence"] = "document", |
Member
There was a problem hiding this comment.
Why is the default value changed to document, does it have a better effect?
Member
There was a problem hiding this comment.
Why is the default value changed to
document, does it have a better effect?
handle it in next PR (we need refactor the split logic for better effect)
| print(context) | ||
| return json.dumps(context, ensure_ascii=False, indent=2) | ||
| except Exception as e: # pylint: disable=W0718 | ||
| except Exception as e: # pylint: disable=W0718 |
Member
There was a problem hiding this comment.
Is this configuration universal? Does it need to be added to pylint.conf?
Member
There was a problem hiding this comment.
Is this configuration universal? Does it need to be added to
pylint.conf?
No need for now maybe
| """Get max-allowed token length""" | ||
| # TODO: list all models and their max tokens from api | ||
| return 2049 | ||
| return 8192 |
Member
There was a problem hiding this comment.
why increase to 8192？
2049 is outdated (in 2023y)
BTW, this method is not used now (may remove it later)
…texData.id while inserting vertex
imbajin
approved these changes
Oct 10, 2024
Member
There was a problem hiding this comment.
Merge it to avoid blocking other PRs (handle chunk split logic in another PR later) @vichayturen
imbajin
changed the title
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Done:
TODO: