Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add OpenAIEmbeddings special token params for tiktoken #2682

Merged
merged 1 commit into from
Apr 11, 2023
Merged

Add OpenAIEmbeddings special token params for tiktoken #2682

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 18 additions & 2 deletions langchain/embeddings/openai.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,17 @@
from __future__ import annotations

import logging
from typing import Any, Callable, Dict, List, Optional
from typing import (
Any,
Callable,
Dict,
List,
Literal,
Optional,
Set,
Tuple,
Union,
)

import numpy as np
from pydantic import BaseModel, Extra, root_validator
Expand Down Expand Up @@ -99,6 +109,8 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
embedding_ctx_length: int = 8191
openai_api_key: Optional[str] = None
openai_organization: Optional[str] = None
allowed_special: Union[Literal["all"], Set[str]] = set()
disallowed_special: Union[Literal["all"], Set[str], Tuple[()]] = "all"
chunk_size: int = 1000
"""Maximum number of texts to embed in each batch"""
max_retries: int = 6
Expand Down Expand Up @@ -195,7 +207,11 @@ def _get_len_safe_embeddings(
for i, text in enumerate(texts):
# replace newlines, which can negatively affect performance.
text = text.replace("\n", " ")
token = encoding.encode(text)
token = encoding.encode(
text,
allowed_special=self.allowed_special,
disallowed_special=self.disallowed_special,
)
for j in range(0, len(token), self.embedding_ctx_length):
tokens += [token[j : j + self.embedding_ctx_length]]
indices += [i]
Expand Down