Eng 2040 ai r 2 add splitting features to the sdk #546
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
Muhammad-Elmallah
requested review from
ahmetgunduz,
basitanees,
thiago-aixplain and
lucas-aixplain
thiago-aixplain
suggested changes
May 30, 2025
| class Splitter: | ||
| def __init__(self, split: bool, split_by: str, split_length: int, split_overlap: int): | ||
| self.split = split | ||
| self.split_by = split_by |
There was a problem hiding this comment.
Make split_by an enumerator. Should it have a default value?
Should split_length and split_overlap have a default value?
| @@ -144,25 +152,39 @@ def search(self, query: str, top_k: int = 10, filters: List[IndexFilter] = []) - | |||
| } | |||
| return self.run(data=data) | |||
|
|
|||
| def upsert(self, documents: List[Record]) -> ModelResponse: | |||
| def upsert(self, documents: List[Record], splitter: Splitter = None) -> ModelResponse: | |||
There was a problem hiding this comment.
splitter: Optional[Splitter] = None
|
|
||
| Returns: | ||
| ModelResponse: Response from the indexing service | ||
|
|
||
| Example: | ||
| index_model.upsert([Record(value="Hello, world!", value_type="text", uri="", id="1", attributes={})]) | ||
| index_model.upsert([Record(value="Hello, world!", value_type="text", uri="", id="1", attributes={})], splitter=Splitter(split=True, split_by="word", split_length=1, split_overlap=0)) |
There was a problem hiding this comment.
Explain in a line what the splitter does in this example.
| @@ -149,8 +150,8 @@ def test_index_model_with_filter(embedding_model, supplier_params): | |||
| from aixplain.factories import IndexFactory | |||
| from aixplain.modules.model.index_model import IndexFilter, IndexFilterOperator | |||
|
|
|||
| for index in IndexFactory.list()["results"]: | |||
| index.delete() | |||
| # for index in IndexFactory.list()["results"]: | |||
| for index in IndexFactory.list()["results"]: | ||
| index.delete() | ||
| # for index in IndexFactory.list()["results"]: | ||
| # index.delete() |
thiago-aixplain
approved these changes
Jun 2, 2025
Muhammad-Elmallah
deleted the
ENG-2040-ai-r-2-add-splitting-features-to-the-sdk
branch
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.
No description provided.