ContextQMD
Back to Llama Index

DashScope Embeddings

docs/examples/embeddings/dashscope_embeddings.ipynb

0.14.214.0 KB
Original Source

<a href="https://colab.research.google.com/github/run-llama/llama_index/blob/main/docs/examples/embeddings/dashscope_embeddings.ipynb" target="_parent"></a>

python
# DashScope Embeddings

If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙.

python
%pip install llama-index-core
%pip install llama-index-embeddings-dashscope
python
# Set API key
%env DASHSCOPE_API_KEY=YOUR_DASHSCOPE_API_KEY

# you can set API key parameter DashScopeTextEmbedding(model=DashScopeTextEmbeddingModels.TEXT_EMBEDDING_V2, api_key=api_key)
python
# imports
from llama_index.embeddings.dashscope import (
    DashScopeEmbedding,
    DashScopeTextEmbeddingModels,
    DashScopeTextEmbeddingType,
)

# Create embeddings
# text_type=`document` to build index
embedder = DashScopeEmbedding(
    model_name=DashScopeTextEmbeddingModels.TEXT_EMBEDDING_V2,
    text_type=DashScopeTextEmbeddingType.TEXT_TYPE_DOCUMENT,
)
text_to_embedding = ["风急天高猿啸哀", "渚清沙白鸟飞回", "无边落木萧萧下", "不尽长江滚滚来"]
# Call text Embedding
result_embeddings = embedder.get_text_embedding_batch(text_to_embedding)
# requests and embedding result index is correspond to.
for index, embedding in enumerate(result_embeddings):
    if embedding is None:  # if the correspondence request is embedding failed.
        print("The %s embedding failed." % text_to_embedding[index])
    else:
        print("Dimension of embeddings: %s" % len(embedding))
        print(
            "Input: %s, embedding is: %s"
            % (text_to_embedding[index], embedding[:5])
        )
python
# imports
from llama_index.embeddings.dashscope import (
    DashScopeEmbedding,
    DashScopeTextEmbeddingModels,
    DashScopeTextEmbeddingType,
)

# Create embeddings
# text_type=`query` to retrive relevant context.
embedder = DashScopeEmbedding(
    model_name=DashScopeTextEmbeddingModels.TEXT_EMBEDDING_V2,
    text_type=DashScopeTextEmbeddingType.TEXT_TYPE_QUERY,
)
# Call text Embedding
embedding = embedder.get_text_embedding("衣服的质量杠杠的，很漂亮，不枉我等了这么久啊，喜欢，以后还来这里买")
print(f"Dimension of embeddings: {len(embedding)}")
print(embedding[:5])
python
# call batch text embedding
from llama_index.embeddings.dashscope import (
    DashScopeEmbedding,
    DashScopeBatchTextEmbeddingModels,
    DashScopeTextEmbeddingType,
)

embedder = DashScopeEmbedding(
    model_name=DashScopeBatchTextEmbeddingModels.TEXT_EMBEDDING_ASYNC_V2,
    text_type=DashScopeTextEmbeddingType.TEXT_TYPE_DOCUMENT,
)

embedding_result_file_url = embedder.get_batch_text_embedding(
    embedding_file_url="https://dashscope.oss-cn-beijing.aliyuncs.com/samples/text/text-embedding-test.txt"
)
print(embedding_result_file_url)
python
# call multimodal embedding service
from llama_index.embeddings.dashscope import (
    DashScopeEmbedding,
    DashScopeMultiModalEmbeddingModels,
)

embedder = DashScopeEmbedding(
    model_name=DashScopeMultiModalEmbeddingModels.MULTIMODAL_EMBEDDING_ONE_PEACE_V1,
)

embedding = embedder.get_image_embedding(
    img_file_path="https://dashscope.oss-cn-beijing.aliyuncs.com/images/256_1.png"
)
print(f"Dimension of embeddings: {len(embedding)}")
print(embedding[:5])
python
# call multimodal embedding service
from llama_index.embeddings.dashscope import (
    DashScopeEmbedding,
    DashScopeMultiModalEmbeddingModels,
)

embedder = DashScopeEmbedding(
    model_name=DashScopeMultiModalEmbeddingModels.MULTIMODAL_EMBEDDING_ONE_PEACE_V1,
)

input = [
    {"factor": 1, "text": "你好"},
    {
        "factor": 2,
        "audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/cow.flac",
    },
    {
        "factor": 3,
        "image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/256_1.png",
    },
]

embedding = embedder.get_multimodal_embedding(input=input)
print(f"Dimension of embeddings: {len(embedding)}")
print(embedding[:5])