added support for bedrock/claude3 #781

koid · 2024-03-13T05:28:18Z

User description

added support for bedrock/claude3

Type

enhancement, documentation

Description

Added support for new Bedrock Claude3 models in the AI handlers.
Introduced a new configuration option drop_params to ensure compatibility with Claude3 models.
Updated the documentation to guide users on configuring Claude3 models and the new drop_params setting.
Updated the litellm library version to 1.31.10 for enhanced functionality and compatibility.

Changes walkthrough

Relevant files

Enhancement

__init__.py `Add Support for Bedrock Claude3 Models` pr_agent/algo/init.py Added support for `bedrock/anthropic.claude-3-sonnet-20240229-v1:0` and `bedrock/anthropic.claude-3-haiku-20240307-v1:0` models.	+5/-0
litellm_ai_handler.py `Enhance Litellm AI Handler for Claude3 Compatibility` pr_agent/algo/ai_handlers/litellm_ai_handler.py Added condition to drop incompatible parameters when using Claude3 models. Updated `max_tokens` for `AmazonAnthropicClaude3Config`.	+3/-0
configuration.toml `Add Drop Params Configuration Option` pr_agent/settings/configuration.toml Added `drop_params` configuration option in `litellm` section.	+2/-1

Documentation

additional_configurations.md `Update Documentation for Claude3 Model Configuration` docs/docs/usage-guide/additional_configurations.md Updated documentation to include configuration for Claude3 models. Added note on setting `drop_params` for Claude3 compatibility.	+9/-2

Dependencies

requirements.txt `Update Litellm Library Version` requirements.txt Updated `litellm` library version from `1.29.1` to `1.31.10`.	+1/-1

✨ PR-Agent usage:
Comment /help on the PR to get a list of all available PR-Agent tools and their descriptions

koid · 2024-03-13T05:35:02Z

docs/docs/usage-guide/additional_configurations.md


 [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.


AmazonAnthropicClaude3Config does not support temperature parameter

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

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

koid · 2024-03-13T05:40:03Z

pr_agent/algo/ai_handlers/litellm_ai_handler.py

@@ -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


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)

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

koid · 2024-03-13T05:45:59Z

/describe

koid · 2024-03-13T05:58:53Z

/describe

koid · 2024-03-13T06:17:24Z

/help

codiumai-pr-agent-pro · 2024-03-13T06:17:30Z

PR-Agent was enabled for this repository. To use it, please link your git user with your CodiumAI identity here.

PR Agent Walkthrough

🤖 Welcome to the PR Agent, an AI-powered tool for automated pull request analysis, feedback, suggestions and more.

Here is a list of tools you can use to interact with the PR Agent:

Tool	Description	Invoke Interactively 💎
DESCRIBE	Generates PR description - title, type, summary, code walkthrough and labels	Run
REVIEW	Adjustable feedback about the PR, possible issues, security concerns, review effort and more	Run
IMPROVE	Code suggestions for improving the PR.	Run
ANALYZE 💎	Identifies code components that changed in the PR, and enables to interactively generate tests, docs, and code suggestions for each component.	Run
UPDATE CHANGELOG	Automatically updates the changelog.	Run
ADD DOCUMENTATION 💎	Generates documentation to methods/functions/classes that changed in the PR.	Run
ASK	Answering free-text questions about the PR.	[*]
GENERATE CUSTOM LABELS	Generates custom labels for the PR, based on specific guidelines defined by the user	[*]
TEST 💎	Generates unit tests for a specific component, based on the PR code change.	[*]
CI FEEDBACK 💎	Generates feedback and analysis for a failed CI job.	[*]
CUSTOM SUGGESTIONS 💎	Generates custom suggestions for improving the PR code, based on specific guidelines defined by the user.	[*]
SIMILAR ISSUE	Automatically retrieves and presents similar issues.	[*]

(1) Note that each tool be triggered automatically when a new PR is opened, or called manually by commenting on a PR.

(2) Tools marked with [*] require additional parameters to be passed. For example, to invoke the /ask tool, you need to comment on a PR: /ask "<question content>". See the relevant documentation for each tool for more details.

koid · 2024-03-13T14:33:01Z

/describe

codiumai-pr-agent-pro · 2024-03-13T14:33:42Z

PR-Agent was enabled for this repository. To use it, please link your git user with your CodiumAI identity here.

PR Description updated to latest commit (0cdd3bf)

Copy walkthrough table to "Files Changed" Tab

koid · 2024-03-14T07:59:11Z

/describe

codiumai-pr-agent-pro · 2024-03-14T07:59:44Z

PR-Agent was enabled for this repository. To use it, please link your git user with your CodiumAI identity here.

PR Description updated to latest commit (3bae515)

Copy walkthrough table to "Files Changed" Tab

mrT23 · 2024-03-15T10:52:51Z

Hi @koid , thanks for the PR

Is the upgrade for litellm version essential for this PR ?
It sometimes creates problems and conflicts, and I would like to avoid it if possible.
Otherwise, looks good.

As a side note, did you form an impression of Claude-3 opus, compared to GPT4, on code? is it competitive ?

koid · 2024-03-18T01:10:39Z

Hi @mrT23 , thanks for review

The support status for litellm's Claude-3 is as follows, and an update is required.

haiku from version v1.31.9
sonnet from version v1.29.3

I'm sorry, I haven't had the chance to try Claude-3 Opus yet. I plan to try it soon.
I haven't done a strict comparison, but this is my personal opinion:
Sonnet is at a usable level and has advantages in terms of cost and response speed.
I feel that Haiku is at a similar level to GPT-3.5.

mrT23 · 2024-03-18T06:00:20Z

PR Review

⏱️ Estimated effort to review [1-5]	2, because the changes are straightforward and mostly involve configuration updates and minor code adjustments. The documentation and requirements update are clear and well-defined.
🧪 Relevant tests	No
🔍 Possible issues	Possible Bug: The addition of `litellm.drop_params` in `litellm_ai_handler.py` without checking its type or existence could lead to runtime errors if not properly configured.
🔒 Security concerns	No

Code feedback:

relevant file	pr_agent/algo/ai_handlers/litellm_ai_handler.py
suggestion	Consider adding a type check for `litellm.drop_params` to ensure it's a boolean. This prevents potential runtime errors if the configuration is incorrect. [important]
relevant line	litellm.drop_params = get_settings().litellm.drop_params

relevant file	pr_agent/algo/__init__.py
suggestion	Ensure that the model keys added are consistent and correctly formatted. Double-check for any typos or inconsistencies in model naming conventions. [medium]
relevant line	'bedrock/anthropic.claude-3-sonnet-20240229-v1:0': 100000,

relevant file	docs/docs/usage-guide/additional_configurations.md
suggestion	Add a note about the expected type for `drop_params` in the documentation to guide users on proper configuration. [medium]
relevant line	drop_params = true

relevant file	requirements.txt
suggestion	Verify the compatibility of the updated `litellm` library version with the existing codebase to avoid potential integration issues. [important]
relevant line	litellm==1.31.10

✨ Review tool usage guide:

Overview:
The review tool scans the PR code changes, and generates a PR review. The tool can be triggered automatically every time a new PR is opened, or can be invoked manually by commenting on any PR.
When commenting, to edit configurations related to the review tool (pr_reviewer section), use the following template:

/review --pr_reviewer.some_config1=... --pr_reviewer.some_config2=...

With a configuration file, use the following template:

[pr_reviewer]
some_config1=...
some_config2=...

Utilizing extra instructions The `review` tool can be configured with extra instructions, which can be used to guide the model to a feedback tailored to the needs of your project. Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify the relevant sub-tool, and the relevant aspects of the PR that you want to emphasize. Examples for extra instructions: `[pr_reviewer] # /review # extra_instructions=""" In the 'possible issues' section, emphasize the following: - Does the code logic cover relevant edge cases? - Is the code logic clear and easy to understand? - Is the code logic efficient? ... """` Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
How to enable\disable automation When you first install PR-Agent app, the default mode for the `review` tool is: `pr_commands = ["/review", ...]` meaning the `review` tool will run automatically on every PR, with the default configuration. Edit this field to enable/disable the tool, or to change the used configurations
Auto-labels The `review` tool can auto-generate two specific types of labels for a PR: a `possible security issue` label, that detects possible security issues (`enable_review_labels_security` flag) a `Review effort [1-5]: x` label, where x is the estimated effort to review the PR (`enable_review_labels_effort` flag)
Extra sub-tools The `review` tool provides a collection of possible feedbacks about a PR. It is recommended to review the possible options, and choose the ones relevant for your use case. Some of the feature that are disabled by default are quite useful, and should be considered for enabling. For example: `require_score_review`, `require_soc2_ticket`, `require_can_be_split_review`, and more.
Auto-approve PRs By invoking: `/review auto_approve` The tool will automatically approve the PR, and add a comment with the approval. To ensure safety, the auto-approval feature is disabled by default. To enable auto-approval, you need to actively set in a pre-defined configuration file the following: `[pr_reviewer] enable_auto_approval = true` (this specific flag cannot be set with a command line argument, only in the configuration file, committed to the repository) You can also enable auto-approval only if the PR meets certain requirements, such as that the `estimated_review_effort` is equal or below a certain threshold, by adjusting the flag: `[pr_reviewer] maximal_review_effort = 5`
More PR-Agent commands To invoke the PR-Agent, add a comment using one of the following commands: /review: Request a review of your Pull Request. /describe: Update the PR title and description based on the contents of the PR. /improve [--extended]: Suggest code improvements. Extended mode provides a higher quality feedback. /ask <QUESTION>: Ask a question about the PR. /update_changelog: Update the changelog based on the PR's contents. /add_docs 💎: Generate docstring for new components introduced in the PR. /generate_labels 💎: Generate labels for the PR based on the PR's contents. /analyze 💎: Automatically analyzes the PR, and presents changes walkthrough for each component. See the tools guide for more details. To list the possible configuration parameters, add a /config comment.

See the review usage page for a comprehensive guide on using this tool.

koid added 6 commits March 13, 2024 11:10

update litellm

3f66a1f

update max_tokens

d62796a

add config litellm.drop_params

1ed2cd0

add Claude3Config

f94a0fd

update docs

33d2d78

update docs

0cdd3bf

koid commented Mar 13, 2024

View reviewed changes

codiumai-pr-agent-pro bot added documentation Improvements or additions to documentation enhancement New feature or request labels Mar 13, 2024

add claude-3-haiku

3bae515

mrT23 self-requested a review March 15, 2024 10:53

mrT23 added the Review effort [1-5]: 2 label Mar 17, 2024

mrT23 approved these changes Mar 18, 2024

View reviewed changes

mrT23 merged commit dd83b19 into Codium-ai:main Mar 18, 2024

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

added support for bedrock/claude3 #781

added support for bedrock/claude3 #781

koid commented Mar 13, 2024 •

edited by codiumai-pr-agent-pro bot

Loading

koid Mar 13, 2024 •

edited

Loading

koid Mar 13, 2024

koid Mar 13, 2024

koid Mar 13, 2024

koid commented Mar 13, 2024

koid commented Mar 13, 2024

koid commented Mar 13, 2024

codiumai-pr-agent-pro bot commented Mar 13, 2024

koid commented Mar 13, 2024

codiumai-pr-agent-pro bot commented Mar 13, 2024

koid commented Mar 14, 2024

codiumai-pr-agent-pro bot commented Mar 14, 2024

mrT23 commented Mar 15, 2024

koid commented Mar 18, 2024

mrT23 commented Mar 18, 2024

added support for bedrock/claude3 #781

added support for bedrock/claude3 #781

Conversation

koid commented Mar 13, 2024 • edited by codiumai-pr-agent-pro bot Loading

User description

Type

Description

Changes walkthrough

koid Mar 13, 2024 • edited Loading

Choose a reason for hiding this comment

koid Mar 13, 2024

Choose a reason for hiding this comment

koid Mar 13, 2024

Choose a reason for hiding this comment

koid Mar 13, 2024

Choose a reason for hiding this comment

koid commented Mar 13, 2024

koid commented Mar 13, 2024

koid commented Mar 13, 2024

codiumai-pr-agent-pro bot commented Mar 13, 2024

PR Agent Walkthrough

koid commented Mar 13, 2024

codiumai-pr-agent-pro bot commented Mar 13, 2024

koid commented Mar 14, 2024

codiumai-pr-agent-pro bot commented Mar 14, 2024

mrT23 commented Mar 15, 2024

koid commented Mar 18, 2024

mrT23 commented Mar 18, 2024

PR Review

koid commented Mar 13, 2024 •

edited by codiumai-pr-agent-pro bot

Loading

koid Mar 13, 2024 •

edited

Loading