mirror of
https://github.com/tencentmusic/supersonic.git
synced 2025-12-10 11:07:06 +00:00
d79f73eab6
* 1.refactor the retrieval module. 2.refactor the http service module. 3.upgrade text2sql output format the parse for absolute time related expression in query. * fix bug. * upgrade the config module, now support config llm suppoted by langchain. * fix conflicts. * update text2sql config reload to be compitable with new config format. * modify default config. * 1.add self-consistency feature for text2sql. 2.upgrade llm api call from sync to async. 3.refactor text2sql module. 4. refactor semantical retriever modules. * merege with upstream master * add general retrieve service. * add api service for sql_agent for crud opereations of few-shots examples. * modify requirements * add auto-cot feature --------- Co-authored-by: shaoweigong <shaoweigong@tencent.com>
24 lines
644 B
Python
24 lines
644 B
Python
# -*- coding:utf-8 -*-
|
|
from typing import List
|
|
|
|
from chromadb.api.types import Documents, EmbeddingFunction, Embeddings
|
|
from langchain.embeddings import HuggingFaceEmbeddings
|
|
|
|
from config.config_parse import HF_TEXT2VEC_MODEL_NAME
|
|
|
|
hg_embedding = HuggingFaceEmbeddings(model_name=HF_TEXT2VEC_MODEL_NAME)
|
|
|
|
|
|
class Text2VecEmbeddingFunction(EmbeddingFunction):
|
|
def __call__(self, texts: Documents) -> Embeddings:
|
|
|
|
embeddings = hg_embedding.embed_documents(texts)
|
|
|
|
return embeddings
|
|
|
|
|
|
def get_embeddings(documents: List[str]) -> List[List[float]]:
|
|
embeddings = hg_embedding.embed_documents(documents)
|
|
|
|
return embeddings
|