Change Fast Embedder adapter using langchain class

[valentimarco]

Description

Change Fast Embedder adapter with langchain class already with cache folder (in core/local_cache, created at runtime if don't exist)

Type of change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

Checklist:

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• Tested Embedder class before this PR

[pieroit]

So no external container?
How much does the core image grow?

[valentimarco]

depends on the size of the model:

model	dim	description	size_in_GB
BAAI/bge-small-en	384	Fast English model	0.20
BAAI/bge-small-en-v1.5	384	Fast and Default English model	0.13
BAAI/bge-base-en	768	Base English model	0.50
BAAI/bge-base-en-v1.5	768	Base English model, v1.5	0.44
sentence-transformers/all-MiniLM-L6-v2	384	Sentence Transformer model, MiniLM-L6-v2	0.09
intfloat/multilingual-e5-large	1024	Multilingual model, e5-large. Recommend using this model for non-English languages	2.24

by default is intfloat/multilingual-e5-large but all models are downloaded and cached in the volume folder. Idk the size of cat + embedder but i don't think we have problem of space...

[valentimarco]

Fresh install with only intfloat/multilingual-e5-large installed