Skip to content

Add tenacity as a dependency to support LM retries with LiteLLM #1731

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
merged 2 commits into from
Oct 31, 2024
Merged

Add tenacity as a dependency to support LM retries with LiteLLM #1731

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5beff76
Tenacity
dbczumar Oct 31, 2024
b8aaef3
Add to non-poetry
dbczumar Oct 31, 2024
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
4 changes: 2 additions & 2 deletions poetry.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

4 changes: 3 additions & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,8 @@ dependencies = [
"magicattr~=0.1.6",
"litellm",
"diskcache",
"json-repair"
"json-repair",
"tenacity>=8.2.3",
Copy link
Collaborator Author

@dbczumar dbczumar Oct 31, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LiteLLM uses tenacity==8.2.3 for testing: https://github.com/BerriAI/litellm/blob/b73039b28337c04ac87eea8e0be11186f142f38f/requirements.txt#L46.

I've confirmed that 8.2.3 and 9.0.0 appear to work just fine via the following script using an Azure OpenAI + Databricks endpoint with an aggressive rate limit of 1QPM:

import litellm
import uuid


litellm.set_verbose=True
for i in range(100):
    print(litellm.completion(
        model="databricks/coreyazureopenai",
        messages=[{"role": "user", "content": "You are a helpful assistant." + uuid.uuid4().hex}],
        retry_strategy="exponential_backoff_retry",
        num_retries=10,
    ))

Accordingly, >=8.2.3 appears appropriate

]

[project.optional-dependencies]
Expand Down Expand Up @@ -137,6 +138,7 @@ magicattr = "^0.1.6"
litellm = "1.49.1"
diskcache = "^5.6.0"
json-repair = "^0.30.0"
tenacity = ">=8.2.3"

[tool.poetry.group.dev.dependencies]
pytest = "^6.2.5"
Expand Down
9 changes: 5 additions & 4 deletions requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,17 +1,18 @@
backoff
datasets
diskcache
httpx
joblib~=1.3
json-repair
litellm<=1.49.1
magicattr~=0.1.6
openai
optuna
pandas
pydantic~=2.0
regex
requests
structlog
tenacity>=8.2.3
Copy link
Collaborator Author

@dbczumar dbczumar Oct 31, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is the only material change. Everything else is just linter formatting

tqdm
ujson
httpx
magicattr~=0.1.6
diskcache
json-repair
Loading