mirror of https://github.com/hwchase17/langchain
LLMRails Embedding (#10959)
LLMRails Embedding Integration This PR provides integration with LLMRails. Implemented here are: langchain/embeddings/llm_rails.py docs/extras/integrations/text_embedding/llm_rails.ipynb Hi @hwchase17 after adding our vectorstore integration to langchain with confirmation of you and @baskaryan, now we want to add our embedding integration --------- Co-authored-by: Anar Aliyev <aaliyev@mgmt.cloudnet.services> Co-authored-by: Bagatur <baskaryan@gmail.com>pull/10640/head
parent
94e31647bd
commit
ff732e10f8
@ -0,0 +1,133 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "278b6c63",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# LLMRails\n",
|
||||||
|
"\n",
|
||||||
|
"Let's load the LLMRails Embeddings class.\n",
|
||||||
|
"\n",
|
||||||
|
"To use LLMRails embedding you need to pass api key by argument or set it in environment with `LLM_RAILS_API_KEY` key.\n",
|
||||||
|
"To gey API Key you need to sign up in https://console.llmrails.com/signup and then go to https://console.llmrails.com/api-keys and copy key from there after creating one key in platform."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"id": "0be1af71",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.embeddings import LLMRailsEmbeddings"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "2c66e5da",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"embeddings = LLMRailsEmbeddings(model='embedding-english-v1') # or embedding-multi-v1"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 3,
|
||||||
|
"id": "01370375",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"text = \"This is a test document.\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "a42e4035",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"To generate embeddings, you can either query an invidivual text, or you can query a list of texts."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 4,
|
||||||
|
"id": "91bc875d-829b-4c3d-8e6f-fc2dda30a3bd",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"[-0.09996652603149414,\n",
|
||||||
|
" 0.015568195842206478,\n",
|
||||||
|
" 0.17670190334320068,\n",
|
||||||
|
" 0.16521021723747253,\n",
|
||||||
|
" 0.21193109452724457]"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 4,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"query_result = embeddings.embed_query(text)\n",
|
||||||
|
"query_result[:5]"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 6,
|
||||||
|
"id": "a4b0d49e-0c73-44b6-aed5-5b426564e085",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"[-0.04242777079343796,\n",
|
||||||
|
" 0.016536075621843338,\n",
|
||||||
|
" 0.10052520781755447,\n",
|
||||||
|
" 0.18272875249385834,\n",
|
||||||
|
" 0.2079043835401535]"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 6,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"doc_result = embeddings.embed_documents([text])\n",
|
||||||
|
"doc_result[0][:5]"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"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": "3.11.5"
|
||||||
|
},
|
||||||
|
"vscode": {
|
||||||
|
"interpreter": {
|
||||||
|
"hash": "e971737741ff4ec9aff7dc6155a1060a59a8a6d52c757dbbe66bf8ee389494b1"
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
@ -0,0 +1,72 @@
|
|||||||
|
""" This file is for LLMRails Embedding """
|
||||||
|
import logging
|
||||||
|
import os
|
||||||
|
from typing import List, Optional
|
||||||
|
|
||||||
|
import requests
|
||||||
|
|
||||||
|
from langchain.pydantic_v1 import BaseModel, Extra
|
||||||
|
from langchain.schema.embeddings import Embeddings
|
||||||
|
|
||||||
|
|
||||||
|
class LLMRailsEmbeddings(BaseModel, Embeddings):
|
||||||
|
"""LLMRails embedding models.
|
||||||
|
|
||||||
|
To use, you should have the environment
|
||||||
|
variable ``LLM_RAILS_API_KEY`` set with your API key or pass it
|
||||||
|
as a named parameter to the constructor.
|
||||||
|
|
||||||
|
Model can be one of ["embedding-english-v1","embedding-multi-v1"]
|
||||||
|
|
||||||
|
Example:
|
||||||
|
.. code-block:: python
|
||||||
|
|
||||||
|
from langchain.embeddings import LLMRailsEmbeddings
|
||||||
|
cohere = LLMRailsEmbeddings(
|
||||||
|
model="embedding-english-v1", api_key="my-api-key"
|
||||||
|
)
|
||||||
|
"""
|
||||||
|
|
||||||
|
model: str = "embedding-english-v1"
|
||||||
|
"""Model name to use."""
|
||||||
|
|
||||||
|
api_key: Optional[str] = None
|
||||||
|
"""LLMRails API key."""
|
||||||
|
|
||||||
|
class Config:
|
||||||
|
"""Configuration for this pydantic object."""
|
||||||
|
|
||||||
|
extra = Extra.forbid
|
||||||
|
|
||||||
|
def embed_documents(self, texts: List[str]) -> List[List[float]]:
|
||||||
|
"""Call out to Cohere's embedding endpoint.
|
||||||
|
|
||||||
|
Args:
|
||||||
|
texts: The list of texts to embed.
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
List of embeddings, one for each text.
|
||||||
|
"""
|
||||||
|
api_key = self.api_key or os.environ.get("LLM_RAILS_API_KEY")
|
||||||
|
if api_key is None:
|
||||||
|
logging.warning("Can't find LLMRails credentials in environment.")
|
||||||
|
raise ValueError("LLM_RAILS_API_KEY is not set")
|
||||||
|
|
||||||
|
response = requests.post(
|
||||||
|
"https://api.llmrails.com/v1/embeddings",
|
||||||
|
headers={"X-API-KEY": api_key},
|
||||||
|
json={"input": texts, "model": self.model},
|
||||||
|
timeout=60,
|
||||||
|
)
|
||||||
|
return [item["embedding"] for item in response.json()["data"]]
|
||||||
|
|
||||||
|
def embed_query(self, text: str) -> List[float]:
|
||||||
|
"""Call out to Cohere's embedding endpoint.
|
||||||
|
|
||||||
|
Args:
|
||||||
|
text: The text to embed.
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
Embeddings for the text.
|
||||||
|
"""
|
||||||
|
return self.embed_documents([text])[0]
|
Loading…
Reference in New Issue