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>

rag/llm/__init__.py

@@ -24,7 +24,8 @@ EmbeddingModel = {
     "Xinference": XinferenceEmbed,
     "Tongyi-Qianwen": HuEmbedding, #QWenEmbed,
     "ZHIPU-AI": ZhipuEmbed,
-    "Moonshot": HuEmbedding
+    "Moonshot": HuEmbedding,
+    "FastEmbed": FastEmbed
 }