mirror of
https://github.com/hwchase17/langchain
synced 2024-10-31 15:20:26 +00:00
594f195e54
- Description: Adds AwaEmbeddings class for embeddings, which provides users with a convenient way to do fine-tuning, as well as the potential need for multimodality - Tag maintainer: @baskaryan Create `Awa.ipynb`: an example notebook for AwaEmbeddings class Modify `embeddings/__init__.py`: Import the class Create `embeddings/awa.py`: The embedding class Create `embeddings/test_awa.py`: The test file. --------- Co-authored-by: taozhiwang <taozhiwa@gmail.com>
110 lines
2.3 KiB
Plaintext
110 lines
2.3 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "b14a24db",
|
|
"metadata": {},
|
|
"source": [
|
|
"# AwaEmbedding\n",
|
|
"\n",
|
|
"This notebook explains how to use AwaEmbedding, which is included in [awadb](https://github.com/awa-ai/awadb), to embedding texts in langchain."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "0ab948fc",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# pip install awadb"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "67c637ca",
|
|
"metadata": {},
|
|
"source": [
|
|
"## import the library"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "5709b030",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.embeddings import AwaEmbeddings"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "1756b1ba",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"Embedding = AwaEmbeddings()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "4a2a098d",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Set embedding model\n",
|
|
"Users can use `Embedding.set_model()` to specify the embedding model. \\\n",
|
|
"The input of this function is a string which represents the model's name. \\\n",
|
|
"The list of currently supported models can be obtained [here](https://github.com/awa-ai/awadb) \\ \\ \n",
|
|
"\n",
|
|
"The **default model** is `all-mpnet-base-v2`, it can be used without setting."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "584b9af5",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"text = \"our embedding test\"\n",
|
|
"\n",
|
|
"Embedding.set_model(\"all-mpnet-base-v2\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "be18b873",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"res_query = Embedding.embed_query(\"The test information\")\n",
|
|
"res_document = Embedding.embed_documents([\"test1\", \"another test\"])"
|
|
]
|
|
}
|
|
],
|
|
"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": "3.11.4"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|