Metadata-Version: 2.1
Name: llama-index-embeddings-modelscope
Version: 0.3.0
Summary: llama-index embeddings modelscope integration
License: MIT
Author: ModelScope
Author-email: modelscope@list.alibaba-inc.com
Requires-Python: >=3.8.1,<3.12
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Requires-Dist: llama-index-core (>=0.11.0,<0.12.0)
Requires-Dist: modelscope[framework] (>=1.12.0)
Requires-Dist: ms-swift
Requires-Dist: sentencepiece
Requires-Dist: torch (>=2.1.2,<3.0.0)
Requires-Dist: transformers[torch] (>=4.37.0,<5.0.0)
Description-Content-Type: text/markdown

# LlamaIndex Embedding Integration: ModelScope

## Installation

To install the required package, run:

```bash
!pip install llama-index-embeddings-modelscope
```

## Basic Usage

### Initialize the ModelScopeLLM

To use the ModelScopeEmbedding model, create an instance by specifying the model name and revision:

```python
from llama_index.embeddings.modelscope.base import ModelScopeEmbedding

model = ModelScopeEmbedding(
    model_name="iic/nlp_gte_sentence-embedding_chinese-base",
    model_revision="master",
)
```

### Generate Embedding

To generate a text embedding for a query, use the `get_query_embedding` method or `get_text_embedding` method:

```python
rsp = model.get_query_embedding("Hello, who are you?")
print(rsp)

rsp = model.get_text_embedding("Hello, who are you?")
print(rsp)
```

### Generate Batch Embedding

To generate a text embedding for a batch of text, use the `get_text_embedding_batch` method:

```python
rsp = model.get_text_embedding_batch(
    ["Hello, who are you?", "I am a student."]
)
print(rsp)
```

