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

Jump to bottom

added support for bedrock/claude3 #781

Merged
merged 7 commits into from
Mar 18, 2024
Merged

added support for bedrock/claude3 #781

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
3f66a1f
update litellm
Mar 13, 2024
d62796a
update max_tokens
Mar 13, 2024
1ed2cd0
add config litellm.drop_params
Mar 13, 2024
f94a0fd
add Claude3Config
Mar 13, 2024
33d2d78
update docs
Mar 13, 2024
0cdd3bf
update docs
Mar 13, 2024
3bae515
add claude-3-haiku
Mar 14, 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
11 changes: 9 additions & 2 deletions docs/docs/usage-guide/additional_configurations.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -162,15 +162,22 @@ To use Amazon Bedrock and its foundational models, add the below configuration:

```
[config] # in configuration.toml
model = "anthropic.claude-v2"
fallback_models="anthropic.claude-instant-v1"
model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
model_turbo="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
fallback_models=["bedrock/anthropic.claude-v2:1"]

[aws] # in .secrets.toml
bedrock_region = "us-east-1"
```

Note that you have to add access to foundational models before using them. Please refer to [this document](https://docs.aws.amazon.com/bedrock/latest/userguide/setting-up.html) for more details.

If you are using the claude-3 model, please configure the following settings as there are parameters incompatible with claude-3.
Copy link
Author

@koid koid Mar 13, 2024 •
edited
Loading

Choose a reason for hiding this comment

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

AmazonAnthropicClaude3Config does not support temperature parameter

https://github.com/BerriAI/litellm/blob/1b93ada827c652eed5f4d8ac05b222b10222b80d/litellm/llms/bedrock.py#L79-L87

Copy link
Author

Choose a reason for hiding this comment

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

Discussion:
Another approach could be to set the temperature only if the model is bedrock's claude3 within the chat_completion function.

```
[litellm]
drop_params = true
```

AWS session is automatically authenticated from your environment, but you can also explicitly set `AWS_ACCESS_KEY_ID` and `AWS_SECRET_ACCESS_KEY` environment variables.


Expand Down
5 changes: 5 additions & 0 deletions pr_agent/algo/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,4 +23,9 @@
'anthropic.claude-v1': 100000,
'anthropic.claude-v2': 100000,
'anthropic/claude-3-opus-20240229': 100000,
'bedrock/anthropic.claude-instant-v1': 100000,
'bedrock/anthropic.claude-v2': 100000,
'bedrock/anthropic.claude-v2:1': 100000,
'bedrock/anthropic.claude-3-sonnet-20240229-v1:0': 100000,
'bedrock/anthropic.claude-3-haiku-20240307-v1:0': 100000,
}
3 changes: 3 additions & 0 deletions pr_agent/algo/ai_handlers/litellm_ai_handler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,8 @@ def __init__(self):
assert litellm_token, "LITELLM_TOKEN is required"
os.environ["LITELLM_TOKEN"] = litellm_token
litellm.use_client = True
if get_settings().get("LITELLM.DROP_PARAMS", None):
litellm.drop_params = get_settings().litellm.drop_params
if get_settings().get("OPENAI.ORG", None):
litellm.organization = get_settings().openai.org
if get_settings().get("OPENAI.API_TYPE", None):
Expand Down Expand Up @@ -68,6 +70,7 @@ def __init__(self):
)
if get_settings().get("AWS.BEDROCK_REGION", None):
litellm.AmazonAnthropicConfig.max_tokens_to_sample = 2000
litellm.AmazonAnthropicClaude3Config.max_tokens = 2000
Copy link
Author

Choose a reason for hiding this comment

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

In litellm, a separate Config class is created for AmazonAnthropicClaude3

Similar to the following pull request, the value of max_tokens is hardcoded.
#483 (comment)

Copy link
Author

Choose a reason for hiding this comment

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

Discussion:
Another approach within chat_completion is to handle which configuration to set based on the model, either AmazonAnthropicConfig or AmazonAnthropicClaude3Config.

self.aws_bedrock_client = boto3.client(
service_name="bedrock-runtime",
region_name=get_settings().aws.bedrock_region,
Expand Down
3 changes: 2 additions & 1 deletion pr_agent/settings/configuration.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -192,7 +192,8 @@ pr_commands = [
url = ""

[litellm]
#use_client = false
# use_client = false
# drop_params = false

[pr_similar_issue]
skip_comments = false
Expand Down
2 changes: 1 addition & 1 deletion requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ GitPython==3.1.32
google-cloud-aiplatform==1.35.0
google-cloud-storage==2.10.0
Jinja2==3.1.2
litellm==1.29.1
litellm==1.31.10
loguru==0.7.2
msrest==0.7.1
openai==1.13.3
Expand Down