mirror of
https://github.com/csunny/DB-GPT.git
synced 2025-07-27 05:47:47 +00:00
59 lines
1.8 KiB
Python
59 lines
1.8 KiB
Python
import asyncio
|
|
import os
|
|
|
|
from dbgpt.configs.model_config import MODEL_PATH, PILOT_PATH, ROOT_PATH
|
|
from dbgpt.rag.embedding import DefaultEmbeddingFactory
|
|
from dbgpt_ext.rag import ChunkParameters
|
|
from dbgpt_ext.rag.assembler import EmbeddingAssembler
|
|
from dbgpt_ext.rag.knowledge import KnowledgeFactory
|
|
from dbgpt_ext.storage.vector_store.chroma_store import ChromaStore, ChromaVectorConfig
|
|
|
|
"""Embedding rag example.
|
|
pre-requirements:
|
|
set your embedding model path in your example code.
|
|
```
|
|
embedding_model_path = "{your_embedding_model_path}"
|
|
```
|
|
|
|
Examples:
|
|
..code-block:: shell
|
|
python examples/rag/embedding_rag_example.py
|
|
"""
|
|
|
|
|
|
def _create_vector_connector():
|
|
"""Create vector connector."""
|
|
config = ChromaVectorConfig(
|
|
persist_path=PILOT_PATH,
|
|
)
|
|
|
|
return ChromaStore(
|
|
config,
|
|
name="embedding_rag_test",
|
|
embedding_fn=DefaultEmbeddingFactory(
|
|
default_model_name=os.path.join(MODEL_PATH, "text2vec-large-chinese"),
|
|
).create(),
|
|
)
|
|
|
|
|
|
async def main():
|
|
file_path = os.path.join(ROOT_PATH, "docs/docs/awel/awel.md")
|
|
knowledge = KnowledgeFactory.from_file_path(file_path)
|
|
vector_store = _create_vector_connector()
|
|
chunk_parameters = ChunkParameters(chunk_strategy="CHUNK_BY_SIZE")
|
|
# get embedding assembler
|
|
assembler = EmbeddingAssembler.load_from_knowledge(
|
|
knowledge=knowledge,
|
|
chunk_parameters=chunk_parameters,
|
|
index_store=vector_store,
|
|
)
|
|
assembler.persist()
|
|
# get embeddings retriever
|
|
retriever = assembler.as_retriever(3)
|
|
chunks = await retriever.aretrieve_with_scores("what is awel talk about", 0.3)
|
|
print(f"embedding rag example results:{chunks}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(main())
|