Simplify the BaseComponent inteface (#64)

This change remove `BaseComponent`'s:

- run_raw
- run_batch_raw
- run_document
- run_batch_document
- is_document
- is_batch

Each component is expected to support multiple types of inputs and a single type of output. Since we want the component to work out-of-the-box with both standardized and customized use cases, supporting multiple types of inputs are expected. At the same time, to reduce the complexity of understanding how to use a component, we restrict a component to only have a single output type.

To accommodate these changes, we also refactor some components to remove their run_raw, run_batch_raw... methods, and to decide the common output interface for those components.

Tests are updated accordingly.

Commit changes:

* Add kwargs to vector store's query
* Simplify the BaseComponent
* Update tests
* Remove support for Python 3.8 and 3.9
* Bump version 0.3.0
* Fix github PR caching still use old environment after bumping version

---------

Co-authored-by: ian <ian@cinnamon.is>
This commit is contained in:
Nguyen Trung Duc (john)
2023-11-13 15:10:18 +07:00
committed by GitHub
parent 6095526dc7
commit d79b3744cb
25 changed files with 280 additions and 458 deletions

View File

@@ -60,7 +60,8 @@ def test_retrieving(mock_openai_embedding, tmp_path):
)
index_pipeline(text=Document(text="Hello world"))
output = retrieval_pipeline(text=["Hello world", "Hello world"])
output = retrieval_pipeline(text="Hello world")
output1 = retrieval_pipeline(text="Hello world")
assert len(output) == 2, "Expect 2 results"
assert output[0] == output[1], "Expect identical results"
assert len(output) == 1, "Expect 1 results"
assert output == output1, "Expect identical results"