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>

tests/test_embedding_models.py

@@ -26,7 +26,8 @@ def test_azureopenai_embeddings_raw(openai_embedding_call):
     )
     output = model("Hello world")
     assert isinstance(output, list)
-    assert isinstance(output[0], float)
+    assert isinstance(output[0], list)
+    assert isinstance(output[0][0], float)
     openai_embedding_call.assert_called()
 
 
@@ -53,8 +54,8 @@ def test_azureopenai_embeddings_batch_raw(openai_embedding_call):
     side_effect=lambda *args, **kwargs: None,
 )
 @patch(
-    "langchain.embeddings.huggingface.HuggingFaceBgeEmbeddings.embed_query",
-    side_effect=lambda *args, **kwargs: [1.0, 2.1, 3.2],
+    "langchain.embeddings.huggingface.HuggingFaceBgeEmbeddings.embed_documents",
+    side_effect=lambda *args, **kwargs: [[1.0, 2.1, 3.2]],
 )
 def test_huggingface_embddings(
     langchain_huggingface_embedding_call, sentence_transformers_init
@@ -67,21 +68,23 @@ def test_huggingface_embddings(
 
     output = model("Hello World")
     assert isinstance(output, list)
-    assert isinstance(output[0], float)
+    assert isinstance(output[0], list)
+    assert isinstance(output[0][0], float)
     sentence_transformers_init.assert_called()
     langchain_huggingface_embedding_call.assert_called()
 
 
 @patch(
-    "langchain.embeddings.cohere.CohereEmbeddings.embed_query",
-    side_effect=lambda *args, **kwargs: [1.0, 2.1, 3.2],
+    "langchain.embeddings.cohere.CohereEmbeddings.embed_documents",
+    side_effect=lambda *args, **kwargs: [[1.0, 2.1, 3.2]],
 )
-def test_cohere_embddings(langchain_cohere_embedding_call):
+def test_cohere_embeddings(langchain_cohere_embedding_call):
     model = CohereEmbdeddings(
         model="embed-english-light-v2.0", cohere_api_key="my-api-key"
     )
 
     output = model("Hello World")
     assert isinstance(output, list)
-    assert isinstance(output[0], float)
+    assert isinstance(output[0], list)
+    assert isinstance(output[0][0], float)
     langchain_cohere_embedding_call.assert_called()