Skip to content

Correctly load chunks with larger headers #11010

Correctly load chunks with larger headers

Correctly load chunks with larger headers #11010

This check has been archived and is scheduled for deletion. Learn more about checks retention
GitHub Actions / JUnit Test Report failed Sep 6, 2023 in 0s

5252 tests run, 2807 passed, 2444 skipped, 1 failed.

Annotations

Check failure on line 1697 in deeplake/core/vectorstore/test_deeplake_vectorstore.py

See this annotation in the file changed.

@github-actions github-actions / JUnit Test Report

test_deeplake_vectorstore.test_multiple_embeddings

Failed: Timeout >300.0s
Raw output
local_path = './hub_pytest/test_deeplake_vectorstore/test_multiple_embeddings'

    @pytest.mark.slow
    def test_multiple_embeddings(local_path):
        vector_store = DeepLakeVectorStore(
            path=local_path,
            overwrite=True,
            tensor_params=[
                {
                    "name": "text",
                    "htype": "text",
                },
                {
                    "name": "embedding_1",
                    "htype": "embedding",
                },
                {
                    "name": "embedding_2",
                    "htype": "embedding",
                },
            ],
        )
    
        with pytest.raises(AssertionError):
            vector_store.add(
                text=texts,
                embedding_function=[embedding_fn, embedding_fn],
                embedding_data=[texts],
                embedding_tensor=["embedding_1", "embedding_2"],
            )
    
        with pytest.raises(AssertionError):
            vector_store.add(
                text=texts,
                embedding_function=[embedding_fn, embedding_fn],
                embedding_data=[texts, texts],
                embedding_tensor=["embedding_1"],
            )
    
        with pytest.raises(AssertionError):
            vector_store.add(
                text=texts,
                embedding_function=[embedding_fn],
                embedding_data=[texts, texts],
                embedding_tensor=["embedding_1", "embedding_2"],
            )
    
        vector_store.add(
            text=texts,
            embedding_function=[embedding_fn, embedding_fn],
            embedding_data=[texts, texts],
            embedding_tensor=["embedding_1", "embedding_2"],
        )
    
        vector_store.add(
            text=texts, embedding_1=(embedding_fn, texts), embedding_2=(embedding_fn, texts)
        )
    
        vector_store.add(
            text=texts,
            embedding_function=embedding_fn,
            embedding_data=[texts, texts],
            embedding_tensor=["embedding_1", "embedding_2"],
        )
    
        # test with initial embedding function
        vector_store.embedding_function = embedding_fn
        vector_store.add(
            text=texts,
            embedding_data=[texts, texts],
            embedding_tensor=["embedding_1", "embedding_2"],
        )
    
        number_of_data = 1000
        _texts, embeddings, ids, metadatas, _ = utils.create_data(
            number_of_data=number_of_data, embedding_dim=EMBEDDING_DIM
        )
        vector_store.add(
            text=25 * _texts,
            embedding_function=[embedding_fn3, embedding_fn3],
            embedding_data=[25 * _texts, 25 * _texts],
            embedding_tensor=["embedding_1", "embedding_2"],
        )
>       vector_store.add(
            text=25 * _texts,
            embedding_1=(embedding_fn3, 25 * _texts),
            embedding_2=(embedding_fn3, 25 * _texts),
        )

deeplake/core/vectorstore/test_deeplake_vectorstore.py:1697: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
deeplake/core/vectorstore/deeplake_vectorstore.py:277: in add
    dataset_utils.extend_or_ingest_dataset(
deeplake/core/vectorstore/vector_search/dataset/dataset.py:460: in extend_or_ingest_dataset
    extend(
deeplake/core/vectorstore/vector_search/dataset/dataset.py:445: in extend
    dataset.extend(processed_tensors)
deeplake/core/dataset/dataset.py:3131: in extend
    self.append(
deeplake/util/invalid_view_op.py:22: in inner
    return callable(x, *args, **kwargs)
deeplake/core/dataset/dataset.py:3173: in append
    self._append_or_extend(
deeplake/core/dataset/dataset.py:3047: in _append_or_extend
    tensor.append(v)
deeplake/util/invalid_view_op.py:22: in inner
    return callable(x, *args, **kwargs)
deeplake/core/tensor.py:404: in append
    self.extend([sample], progressbar=False)
deeplake/util/invalid_view_op.py:22: in inner
    return callable(x, *args, **kwargs)
deeplake/core/tensor.py:316: in extend
    self.chunk_engine.extend(
deeplake/core/chunk_engine.py:1080: in extend
    self._extend(samples, progressbar, pg_callback=pg_callback)
deeplake/core/chunk_engine.py:1013: in _extend
    self._samples_to_chunks(
deeplake/core/chunk_engine.py:836: in _samples_to_chunks
    num_samples_added = current_chunk.extend_if_has_space(
deeplake/core/chunk/uncompressed_chunk.py:25: in extend_if_has_space
    return self._extend_if_has_space_text(
deeplake/core/chunk/uncompressed_chunk.py:73: in _extend_if_has_space_text
    csum = np.cumsum(lengths[: num_samples - 1])
<__array_function__ internals>:200: in cumsum
    ???
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

a = array([], dtype=uint32), axis = None, dtype = None, out = None

>   @array_function_dispatch(_cumsum_dispatcher)
E   Failed: Timeout >300.0s

/opt/hostedtoolcache/Python/3.10.12/x64/lib/python3.10/site-packages/numpy/core/fromnumeric.py:2523: Failed