Skip to content

Fallback to gpt-4o for tiktoken if openai model unrecognized #1262

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

Merged
jonahdc merged 3 commits into from
Feb 5, 2025
Merged

Fallback to gpt-4o for tiktoken if openai model unrecognized #1262

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d368576
Fallback to gpt-4o for tiktoken if openai model unrecognized
whoisarpit Feb 5, 2025
6e5c556
Add estimated model limit for o3-mini
whoisarpit Feb 5, 2025
94c4a71
Bump version to 0.0.96
whoisarpit Feb 5, 2025
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
9 changes: 8 additions & 1 deletion patchwork/common/client/llm/openai_.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
from typing_extensions import Dict, Iterable, List, Optional, Union

from patchwork.common.client.llm.protocol import NOT_GIVEN, LlmClient, NotGiven
from patchwork.logger import logger


@functools.lru_cache
Expand All @@ -36,6 +37,7 @@ class OpenAiLlmClient(LlmClient):
"o1-mini": 128_000,
"gpt-4o-mini": 128_000,
"gpt-4o": 128_000,
"o3-mini": 128_000,
}

def __init__(self, api_key: str, base_url=None, **kwargs):
Expand Down Expand Up @@ -87,7 +89,12 @@ def is_prompt_supported(

model_limit = self.__get_model_limits(model)
token_count = 0
encoding = tiktoken.encoding_for_model(model)
encoding = None
try:
encoding = tiktoken.encoding_for_model(model)
except Exception as e:
logger.error(f"Error getting encoding for model {model}: {e}, using gpt-4o as fallback")
encoding = tiktoken.encoding_for_model("gpt-4o")
for message in messages:
message_token_count = len(encoding.encode(message.get("content")))
token_count = token_count + message_token_count
Expand Down
2 changes: 1 addition & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
[tool.poetry]
name = "patchwork-cli"
version = "0.0.95"
version = "0.0.96"
description = ""
authors = ["patched.codes"]
license = "AGPL"
Expand Down