feat:update heurist env var examples

[tsubasakong]

Relates to

• Update Heurist model configurations and add embedding support

Risks

Low - Configuration updates for Heurist models and embedding support

Background

What does this PR do?

• Updates LARGE_HEURIST_MODEL from llama-3.1-405b to llama-3.3-70b
• Changes HEURIST_IMAGE_MODEL from PepeXL to FLUX.1-dev
• Adds HEURIST_EMBEDDING_MODEL configuration (BAAI/bge-large-en-v1.5)
• Adds USE_HEURIST_EMBEDDING configuration option for toggling between Heurist and local embedding

What kind of change is this?

Updates (new versions of included code)
Improvements (misc. changes to existing features)

Documentation changes needed?

My changes require a change to the project documentation to reflect the new model versions and embedding configuration options.

Testing

Where should a reviewer start?

1. Review the .env.example changes for new configuration options
2. Verify model version updates align with available models
3. Test embedding functionality when USE_HEURIST_EMBEDDING is enabled/disabled

Detailed testing steps

• Verify LARGE_HEURIST_MODEL works with meta-llama/llama-3.3-70b
• Test FLUX.1-dev image model integration
• Validate BAAI/bge-large-en-v1.5 embedding model functionality
• Test switching between Heurist and local embedding using USE_HEURIST_EMBEDDING flag

Deploy Notes

• Update environment variables in production to reflect new model versions
• Ensure Heurist API access is configured for new models

[coderabbitai]

📝 Walkthrough

Walkthrough

The pull request updates the .env.example configuration file for the Heurist model, introducing changes to model specifications and embedding settings. The primary modifications include updating the large language model to Llama 3.3-70b-instruct, changing the image model to FLUX.1-dev, and adding new configuration options for embedding functionality.

Changes

File	Changes
.env.example	- Updated LARGE_HEURIST_MODEL from meta-llama/llama-3.1-405b-instruct to meta-llama/llama-3.3-70b-instruct - Changed HEURIST_IMAGE_MODEL from PepeXL to FLUX.1-dev - Added HEURIST_EMBEDDING_MODEL with default BAAI/bge-large-en-v1.5 - Added USE_HEURIST_EMBEDDING configuration option

---

📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between e9e5608 and 16cdf9c.

📒 Files selected for processing (1)

• .env.example (1 hunks)

🔇 Additional comments (2)

.env.example (2)

240-241: LGTM! New embedding configuration looks good.

The addition of HEURIST_EMBEDDING_MODEL with BAAI/bge-large-en-v1.5 and the USE_HEURIST_EMBEDDING toggle provides flexibility in choosing between Heurist and local embedding.

---

238-239: Verify model compatibility and performance implications.

The changes to model versions (LARGE_HEURIST_MODEL and HEURIST_IMAGE_MODEL) represent significant updates. While llama-3.3-70b-instruct is newer than llama-3.1-405b, it has a smaller parameter count which could affect performance characteristics.

Run this script to check model availability and version compatibility:

✅ Verification successful

Model updates are properly integrated and safe to use

The changes align with the codebase's supported models. While llama-3.3-70b-instruct has fewer parameters than its predecessor, it compensates with a newer architecture and specialized instruction tuning. FLUX.1-dev is properly configured as the default image model throughout the system.

🏁 Scripts executed

The following scripts were executed for the analysis:

Script:

#!/bin/bash
# Description: Verify model versions and their availability in the codebase
# Check for any hardcoded model version references
rg -i "llama-3\.[1-3]|FLUX\.1-dev|PepeXL" --type python

Length of output: 88

---

Script:

#!/bin/bash
# Search for model references in all files
rg -i "llama-3\.[1-3]|FLUX\.1-dev|PepeXL" -A 2

# Search for model configuration handling
ast-grep --pattern 'model = $_ || MODEL = $_'

# Search for any environment variable loading related to these models
rg -i "(LARGE_HEURIST_MODEL|HEURIST_IMAGE_MODEL)" -A 2

Length of output: 20898

---

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Generate unit testing code for this file.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai generate unit testing code for this file.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and generate unit testing code.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate docstrings to generate docstrings for this PR. (Beta)
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.