Add context manager streaming support for Anthropic

[devin-ai-integration]

🔍 Review Summary

Purpose

This update enhances the Anthropic provider by implementing context handler streaming, thus enabling synchronous and asynchronous message streaming, featuring a new model version claude-3-sonnet-20240229.

Key Changes

• New Feature

  • Added create_stream and __call__ methods for context handler streaming.
  • Integrated model claude-3-sonnet-20240229 to the AnthropicProvider class.

• Enhancement

  • Enhanced example scripts to demonstrate evolving context handler pattern for both synchronous and asynchronous streaming.

• Test

  • Updated and expanded test cases for the new model version.
  • Provided comprehensive coverage of the streaming patterns.

Impact

• Accelerates and optimizes the streaming process by introducing new methods.
• Ensures robustness by providing comprehensive test case coverage.
• Improves understanding of the new features through updated example scripts.

Original Description

No existing description found

[devin-ai-integration]

🤖 Devin AI Engineer

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

• Address comments on this PR
• Look at CI failures and help fix them

⚙️ Control Options:

• Disable automatic comment and CI monitoring

Add "(aside)" to your comment to have me ignore it.

[entelligence-ai-pr-reviews]

Walkthrough

This update enhances the Anthropic provider by implementing context handler streaming, enabling both synchronous and asynchronous message streaming. Key changes include the addition of create_stream and __call__ methods in the AnthropicProvider class, and the update of the model version to claude-3-sonnet-20240229. New example scripts and updates to existing ones demonstrate the context handler pattern for streaming. Test cases have been revised to ensure compatibility and coverage with the new model version.

Changes

File(s)	Summary
agentops/llms/providers/anthropic.py	Added create_stream and __call__ methods for context handler streaming; updated to model claude-3-sonnet-20240229.
examples/anthropic_examples/anthropic-example-async.ipynb	Updated async example to demonstrate context handler streaming with the new model version.
examples/anthropic_examples/anthropic-example-sync.ipynb	Updated sync example to demonstrate context handler streaming with the new model version.
examples/anthropic_examples/anthropic-example-async.py	Introduced new async example script showcasing context handler pattern for streaming.
tests/core_manual_tests/providers/anthropic_canary.py	Updated test cases for new model version and comprehensive streaming pattern coverage.

🔗 Related PRs

• [Docs] Update and clean existing docs for better readability #558: Updated and cleaned integration documentation for better readability and developer experience, including new pages for AI21, Groq, and Mistral AI, along with structural improvements and example updates.
• Reorganize Dependencies and CI packaging #540: The pull request Reorganize Dependencies and CI packaging #540 introduces a new [dependency-groups] following PEP 735, moves the tach package to a ci group, and updates the GitHub action accordingly, ensuring CI workflows remain functional without altering the development environment setup.
• fix tests #562: A pull request addresses issues with newer PsUtil versions failing tests by removing unused arguments in tuples.
• deps: remove packaging; unpinned & ranged versioning #561: The pull request addresses issues [Bug]: Stop pinning dependency versions #545, Loosen Dependency Restriction for packaging Version #556, and [Feature]: Loosen Dependency Restriction for packaging Version #555, clarifies packaging dependencies, restores a previous psutil dependency, and caps all dependencies to their latest stable versions for security and performance reasons.

Instructions

Emoji Descriptions:

• ⚠️ Potential Issue - May require further investigation.
• 🔒 Security Vulnerability - Fix to ensure system safety.
• 💻 Code Improvement - Suggestions to enhance code quality.
• 🔨 Refactor Suggestion - Recommendations for restructuring code.
• ℹ️ Others - General comments and information.

Interact with the Bot:

• Send a message or request using the format:
  @bot + *your message*

Example: @bot Can you suggest improvements for this code?

• Help the Bot learn by providing feedback on its responses.
  @bot + *feedback*

Example: @bot Do not comment on `save_auth` function !

Execute a command using the format:

@bot + */command*

Example: @bot /updateCommit

Available Commands:

• /updateCommit ✨: Apply the suggested changes and commit them (or Click on the Github Action button to apply the changes !)
• /updateGuideline 🛠️: Modify an existing guideline.
• /addGuideline ➕: Introduce a new guideline.

Tips for Using @bot Effectively:

• Specific Queries: For the best results, be specific with your requests.
  🔍 Example: @bot summarize the changes in this PR.
• Focused Discussions: Tag @bot directly on specific code lines or files for detailed feedback.
  📑 Example: @bot review this line of code.
• Managing Reviews: Use review comments for targeted discussions on code snippets, and PR comments for broader queries about the entire PR.
  💬 Example: @bot comment on the entire PR.

Need More Help?

📚 Visit our documentation for detailed guides on using Entelligence.AI.
🌐 Join our community to connect with others, request features, and share feedback.
🔔 Follow us for updates on new features and improvements.