community: Add Laser Embedding Integration (#18111)

- **Description:** Added Integration with Meta AI's LASER
Language-Agnostic SEntence Representations embedding library, which
supports multilingual embedding for any of the languages listed here:
https://github.com/facebookresearch/flores/blob/main/flores200/README.md#languages-in-flores-200,
including several low resource languages
- **Dependencies:** laser_encoders
This commit is contained in:
Dan Stambler
2024-02-26 15:16:37 -05:00
committed by GitHub
parent 257879e98d
commit 69344a0661
5 changed files with 270 additions and 0 deletions

View File

@@ -0,0 +1,149 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "900fbd04-f6aa-4813-868f-1c54e3265385",
"metadata": {},
"source": [
"# LASER Language-Agnostic SEntence Representations Embeddings by Meta AI\n",
"\n",
">[LASER](https://github.com/facebookresearch/LASER/) is a Python library developed by the Meta AI Research team and used for creating multilingual sentence embeddings for over 147 languages as of 2/25/2024 \n",
">- List of supported languages at https://github.com/facebookresearch/flores/blob/main/flores200/README.md#languages-in-flores-200"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "2a773d8d",
"metadata": {},
"source": [
"## Dependencies\n",
"\n",
"To use LaserEmbed with LangChain, install the `laser_encoders` Python package."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "91ea14ce-831d-409a-a88f-30353acdabd1",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"%pip install laser_encoders"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "426f1156",
"metadata": {},
"source": [
"## Imports"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "3f5dc9d7-65e3-4b5b-9086-3327d016cfe0",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain_community.embeddings.laser import LaserEmbeddings"
]
},
{
"cell_type": "markdown",
"id": "8c77b0bb-2613-4167-a204-14d424b59105",
"metadata": {},
"source": [
"## Instantiating Laser\n",
" \n",
"### Parameters\n",
"- `lang: Optional[str]`\n",
" >If empty will default\n",
" to using a multilingual LASER encoder model (called \"laser2\").\n",
" You can find the list of supported languages and lang_codes [here](https://github.com/facebookresearch/flores/blob/main/flores200/README.md#languages-in-flores-200)\n",
" and [here](https://github.com/facebookresearch/LASER/blob/main/laser_encoders/language_list.py)\n",
"."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6fb585dd",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# Ex Instantiationz\n",
"embeddings = LaserEmbeddings(lang=\"eng_Latn\")"
]
},
{
"cell_type": "markdown",
"id": "119fbaad-9442-4fff-8214-c5f597bc8e77",
"metadata": {},
"source": [
"## Usage\n",
"\n",
"### Generating document embeddings"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "62920051-cbd2-460d-ba24-0424c1ed395d",
"metadata": {},
"outputs": [],
"source": [
"document_embeddings = embeddings.embed_documents(\n",
" [\"This is a sentence\", \"This is some other sentence\"]\n",
")"
]
},
{
"cell_type": "markdown",
"id": "7fd10d96-baee-468f-a532-b70b16b78d1f",
"metadata": {},
"source": [
"### Generating query embeddings"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9f793bb6-609a-4a4a-a5c7-8e8597228915",
"metadata": {},
"outputs": [],
"source": [
"query_embeddings = embeddings.embed_query(\"This is a query\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
}