github/DB-GPT
1
0
Fork 0
mirror of https://github.com/csunny/DB-GPT.git synced 2025-09-14 13:40:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor: Refactor proxy LLM (#1064)

Browse Source
This commit is contained in:
Fangyin Cheng
2024-01-14 21:01:37 +08:00
committed by GitHub
parent a035433170
commit 22bfd01c4b
95 changed files with 2049 additions and 1294 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
dbgpt/rag/embedding/embedding_factory.py
View File

@@ -1,6 +1,7 @@
from __future__ import annotations
from abc import ABC, abstractmethod
from typing import Any, Type, TYPE_CHECKING
from typing import TYPE_CHECKING, Any, Type
from dbgpt.component import BaseComponent
from dbgpt.rag.embedding.embeddings import HuggingFaceEmbeddings

22
dbgpt/rag/embedding/embeddings.py
View File

@@ -3,7 +3,7 @@ from abc import ABC, abstractmethod
from typing import Any, Dict, List, Optional
import requests
from pydantic import Field, Extra, BaseModel
from pydantic import BaseModel, Extra, Field
DEFAULT_MODEL_NAME = "sentence-transformers/all-mpnet-base-v2"
DEFAULT_INSTRUCT_MODEL = "hkunlp/instructor-large"
@@ -54,12 +54,12 @@ class HuggingFaceEmbeddings(BaseModel, Embeddings):
from .embeddings import HuggingFaceEmbeddings
model_name = "sentence-transformers/all-mpnet-base-v2"
model_kwargs = {'device': 'cpu'}
encode_kwargs = {'normalize_embeddings': False}
model_kwargs = {"device": "cpu"}
encode_kwargs = {"normalize_embeddings": False}
hf = HuggingFaceEmbeddings(
model_name=model_name,
model_kwargs=model_kwargs,
encode_kwargs=encode_kwargs
encode_kwargs=encode_kwargs,
)
"""
@@ -142,12 +142,12 @@ class HuggingFaceInstructEmbeddings(BaseModel, Embeddings):
from langchain.embeddings import HuggingFaceInstructEmbeddings
model_name = "hkunlp/instructor-large"
model_kwargs = {'device': 'cpu'}
encode_kwargs = {'normalize_embeddings': True}
model_kwargs = {"device": "cpu"}
encode_kwargs = {"normalize_embeddings": True}
hf = HuggingFaceInstructEmbeddings(
model_name=model_name,
model_kwargs=model_kwargs,
encode_kwargs=encode_kwargs
encode_kwargs=encode_kwargs,
)
"""
@@ -221,12 +221,12 @@ class HuggingFaceBgeEmbeddings(BaseModel, Embeddings):
from langchain.embeddings import HuggingFaceBgeEmbeddings
model_name = "BAAI/bge-large-en"
model_kwargs = {'device': 'cpu'}
encode_kwargs = {'normalize_embeddings': True}
model_kwargs = {"device": "cpu"}
encode_kwargs = {"normalize_embeddings": True}
hf = HuggingFaceBgeEmbeddings(
model_name=model_name,
model_kwargs=model_kwargs,
encode_kwargs=encode_kwargs
encode_kwargs=encode_kwargs,
)
"""
@@ -336,7 +336,7 @@ class HuggingFaceInferenceAPIEmbeddings(BaseModel, Embeddings):
hf_embeddings = HuggingFaceInferenceAPIEmbeddings(
api_key="your_api_key",
model_name="sentence-transformers/all-MiniLM-l6-v2"
model_name="sentence-transformers/all-MiniLM-l6-v2",
)
texts = ["Hello, world!", "How are you?"]
hf_embeddings.embed_documents(texts)