github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-04 20:46:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

community: Fix FastEmbedEmbeddings (#24462)

Browse Source 
## Description

This PR:
- Fixes the validation error in `FastEmbedEmbeddings`.
- Adds support for `batch_size`, `parallel` params.
- Removes support for very old FastEmbed versions.
- Updates the FastEmbed doc with the new params.

Associated Issues:
- Resolves #24039
- Resolves #https://github.com/qdrant/fastembed/issues/296
This commit is contained in:
Anush
2024-07-30 22:12:46 +05:30
committed by GitHub
parent 73ec24fc56
commit 51b15448cc
4 changed files with 69 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
docs/docs/integrations/text_embedding/fastembed.ipynb
View File

@@ -73,16 +73,25 @@
"- `max_length: int` (default: 512)\n",
" > The maximum number of tokens. Unknown behavior for values > 512.\n",
"\n",
"- `cache_dir: Optional[str]`\n",
"- `cache_dir: Optional[str]` (default: None)\n",
" > The path to the cache directory. Defaults to `local_cache` in the parent directory.\n",
"\n",
"- `threads: Optional[int]`\n",
" > The number of threads a single onnxruntime session can use. Defaults to None.\n",
"- `threads: Optional[int]` (default: None)\n",
" > The number of threads a single onnxruntime session can use.\n",
"\n",
"- `doc_embed_type: Literal[\"default\", \"passage\"]` (default: \"default\")\n",
" > \"default\": Uses FastEmbed's default embedding method.\n",
" \n",
" > \"passage\": Prefixes the text with \"passage\" before embedding."
" > \"passage\": Prefixes the text with \"passage\" before embedding.\n",
"\n",
"- `batch_size: int` (default: 256)\n",
" > Batch size for encoding. Higher values will use more memory, but be faster.\n",
"\n",
"- `parallel: Optional[int]` (default: None)\n",
"\n",
" > If `>1`, data-parallel encoding will be used, recommended for offline encoding of large datasets.\n",
" > If `0`, use all available cores.\n",
" > If `None`, don't use data-parallel processing, use default onnxruntime threading instead."
]
},
{

4
docs/docs/integrations/vectorstores/qdrant.ipynb
View File

@@ -317,7 +317,7 @@
"To search with only dense vectors,\n",
"\n",
"- The `retrieval_mode` parameter should be set to `RetrievalMode.DENSE`(default).\n",
"- A [dense embeddings](https://python.langchain.com/v0.2/docs/integrations/text_embedding/) value should be provided for the `embedding` parameter."
"- A [dense embeddings](https://python.langchain.com/v0.2/docs/integrations/text_embedding/) value should be provided to the `embedding` parameter."
]
},
{
@@ -407,7 +407,7 @@
"To perform a hybrid search using dense and sparse vectors with score fusion,\n",
"\n",
"- The `retrieval_mode` parameter should be set to `RetrievalMode.HYBRID`.\n",
"- A [dense embeddings](https://python.langchain.com/v0.2/docs/integrations/text_embedding/) value should be provided for the `embedding` parameter.\n",
"- A [dense embeddings](https://python.langchain.com/v0.2/docs/integrations/text_embedding/) value should be provided to the `embedding` parameter.\n",
"- An implementation of the [`SparseEmbeddings`](https://github.com/langchain-ai/langchain/blob/master/libs/partners/qdrant/langchain_qdrant/sparse_embeddings.py) interface using any sparse embeddings provider has to be provided as value to the `sparse_embedding` parameter.\n",
"\n",
"Note that if you've added documents with the `HYBRID` mode, you can switch to any retrieval mode when searching. Since both the dense and sparse vectors are available in the collection."