ragflow/rag/llm/__init__.py
Anush 826ad6a33a
feat: FastEmbed embedding support (#291)
### Description

Following up on https://github.com/infiniflow/ragflow/pull/275, this PR
adds support for FastEmbed model configurations.

The options are not exhaustive. You can find the full list
[here](https://qdrant.github.io/fastembed/examples/Supported_Models/).

P.S. I ran into OOM issues when building the image.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Co-authored-by: KevinHuSh <kevinhu.sh@gmail.com>
2024-04-15 15:58:06 +08:00

51 lines
1.3 KiB
Python

#
# Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
from .embedding_model import *
from .chat_model import *
from .cv_model import *
EmbeddingModel = {
"Ollama": OllamaEmbed,
"OpenAI": OpenAIEmbed,
"Xinference": XinferenceEmbed,
"Tongyi-Qianwen": HuEmbedding, #QWenEmbed,
"ZHIPU-AI": ZhipuEmbed,
"Moonshot": HuEmbedding,
"FastEmbed": FastEmbed
}
CvModel = {
"OpenAI": GptV4,
"Ollama": OllamaCV,
"Xinference": XinferenceCV,
"Tongyi-Qianwen": QWenCV,
"ZHIPU-AI": Zhipu4V,
"Moonshot": LocalCV
}
ChatModel = {
"OpenAI": GptTurbo,
"ZHIPU-AI": ZhipuChat,
"Tongyi-Qianwen": QWenChat,
"Ollama": OllamaChat,
"Xinference": XinferenceChat,
"Moonshot": MoonshotChat
}