langchain/libs/community/langchain_community/embeddings/llm_rails.py
Harrison Chase 4eda647fdd
infra: add -p to mkdir in lint steps (#17013)
Previously, if this did not find a mypy cache then it wouldnt run

this makes it always run

adding mypy ignore comments with existing uncaught issues to unblock other prs

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-02-05 11:22:06 -08:00

75 lines
2.3 KiB
Python

""" This file is for LLMRails Embedding """
from typing import Dict, List, Optional
import requests
from langchain_core.embeddings import Embeddings
from langchain_core.pydantic_v1 import BaseModel, Extra, SecretStr, root_validator
from langchain_core.utils import convert_to_secret_str, get_from_dict_or_env
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_community.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[SecretStr] = None
"""LLMRails API key."""
class Config:
"""Configuration for this pydantic object."""
extra = Extra.forbid
@root_validator()
def validate_environment(cls, values: Dict) -> Dict:
"""Validate that api key exists in environment."""
api_key = convert_to_secret_str(
get_from_dict_or_env(values, "api_key", "LLM_RAILS_API_KEY")
)
values["api_key"] = api_key
return values
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.
"""
response = requests.post(
"https://api.llmrails.com/v1/embeddings",
headers={"X-API-KEY": self.api_key.get_secret_value()}, # type: ignore[union-attr]
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]