Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
6 changes: 3 additions & 3 deletions .github/ISSUE_TEMPLATE/bug_report.md
Original file line number Diff line number Diff line change
Expand Up @@ -25,9 +25,9 @@ If applicable, add screenshots to help explain your problem.

**Environment (please complete the following information):**
- OS: [e.g. macOS, Windows, Linux]
- Python version: [e.g. 3.9, 3.10]
- Reward Kit version: [e.g. 0.1.0, or commit SHA if from source]
- How installed: [e.g. pip, from source]
- Python version: [e.g. 3.9, 3.10]
- Eval Protocol version: [e.g. 0.1.0, or commit SHA if from source]
- How installed: [e.g. pip, from source]

**Additional context**
Add any other context about the problem here. For example, are you using it with a specific LLM provider, or in a particular environment?
14 changes: 7 additions & 7 deletions development/CONTRIBUTING.md
Original file line number Diff line number Diff line change
Expand Up @@ -360,7 +360,7 @@ uv run black eval_protocol

## Available Reward Functions

Reward Kit includes these out-of-the-box reward functions:
Eval Protocol includes these out-of-the-box reward functions:

| Category | Reward Functions |
|----------|-----------------|
Expand All @@ -380,7 +380,7 @@ Reward Kit includes these out-of-the-box reward functions:

## Running Examples

The examples folder contains sample code for using the Reward Kit:
The examples folder contains sample code for using Eval Protocol:

```bash
# Run evaluation preview example
Expand Down Expand Up @@ -506,7 +506,7 @@ If you encounter authentication issues:
3. **Check Account ID**: Confirm that the `FIREWORKS_ACCOUNT_ID` is correct for the environment you are targeting (e.g., `pyroworks-dev` for the dev API, or your personal account ID).
4. **API Base URL**: If using `FIREWORKS_API_BASE`, ensure it points to the correct API endpoint (e.g., `https://dev.api.fireworks.ai` for development).

You can use the following snippet to check what credentials the Reward Kit is resolving:
You can use the following snippet to check what credentials Eval Protocol is resolving:
```python
from eval_protocol.auth import get_fireworks_api_key, get_fireworks_account_id

Expand Down Expand Up @@ -556,7 +556,7 @@ uv pip install dist/eval_protocol-*.whl

## Contributing Process

We welcome contributions to Reward Kit! Please follow these steps to contribute:
We welcome contributions to Eval Protocol! Please follow these steps to contribute:

1. **Find or Create an Issue**:
* Look for existing issues on the [GitHub Issues page](https://github.com/fireworks-ai/eval-protocol/issues) that you'd like to work on.
Expand All @@ -581,9 +581,9 @@ We welcome contributions to Reward Kit! Please follow these steps to contribute:

6. **Run Code Quality Checks**:

* Format your code: `uv run black reward_kit tests`
* Check linting: `uv run flake8 reward_kit tests`
* Check types: `uv run mypy reward_kit`
* Format your code: `uv run black eval_protocol tests`
* Check linting: `uv run flake8 eval_protocol tests`
* Check types: `uv run mypy eval_protocol`
* Run pre-commit hooks: `pre-commit run --all-files`

7. **Update Documentation**:
Expand Down
2 changes: 1 addition & 1 deletion eval_protocol/__main__.py
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
"""
Main entry point for running reward-kit as a module.
Main entry point for running Eval Protocol as a module.
"""

import sys
Expand Down
2 changes: 1 addition & 1 deletion eval_protocol/_version.py
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,7 @@ def get_config() -> VersioneerConfig:
cfg.VCS = "git"
cfg.style = "pep440"
cfg.tag_prefix = "v"
cfg.parentdir_prefix = "reward-kit-"
cfg.parentdir_prefix = "eval-protocol-"
cfg.versionfile_source = "eval_protocol/_version.py"
cfg.verbose = False
return cfg
Expand Down
6 changes: 3 additions & 3 deletions eval_protocol/cli_commands/deploy.py
Original file line number Diff line number Diff line change
Expand Up @@ -93,7 +93,7 @@ def _establish_local_server_and_tunnel(args):
function_ref = args.function_ref
local_server_port = args.local_port

log_dir = os.path.join(os.getcwd(), "logs", "reward-kit-local")
log_dir = os.path.join(os.getcwd(), "logs", "eval-protocol-local")
os.makedirs(log_dir, exist_ok=True)
generic_server_log_path = os.path.join(log_dir, f"generic_server_{evaluator_id}.log")

Expand Down Expand Up @@ -270,9 +270,9 @@ def _deploy_to_gcp_cloud_run(args, current_config, gcp_config_from_yaml):

gcp_sanitized_eval_id = "".join(filter(lambda char: char.isalnum() or char in ["-", "_"], args.id))
if not gcp_sanitized_eval_id:
gcp_sanitized_eval_id = "rewardkit-evaluator"
gcp_sanitized_eval_id = "evalprotocol-evaluator"
secret_id_for_auth_key = f"rk-eval-{gcp_sanitized_eval_id}-authkey"
secret_labels = {"managed-by": "reward-kit", "evaluator-id": evaluator_id}
secret_labels = {"managed-by": "eval-protocol", "evaluator-id": evaluator_id}

api_key_secret_version_id = ensure_gcp_secret(
project_id=gcp_project_id,
Expand Down
4 changes: 2 additions & 2 deletions eval_protocol/cli_commands/deploy_mcp.py
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@ def _generate_mcp_dockerfile_content(
# Base requirements for MCP servers - matching setup.py dependencies
base_requirements = [
"fastmcp>=0.1.0",
# Core reward-kit dependencies from setup.py
# Core Eval Protocol dependencies from setup.py
"requests>=2.25.0",
"pydantic>=2.0.0",
"dataclasses-json>=0.5.7",
Expand Down Expand Up @@ -154,7 +154,7 @@ def _deploy_mcp_to_gcp_cloud_run(args, current_config, gcp_config_from_yaml):
if not gcp_ar_repo_name and gcp_config_from_yaml:
gcp_ar_repo_name = gcp_config_from_yaml.artifact_registry_repository
if not gcp_ar_repo_name:
gcp_ar_repo_name = "reward-kit-mcp-servers"
gcp_ar_repo_name = "eval-protocol-mcp-servers"

print(f"Using GCP Project: {gcp_project_id}, Region: {gcp_region}, AR Repo: {gcp_ar_repo_name}")

Expand Down
2 changes: 1 addition & 1 deletion eval_protocol/execution/pipeline.py
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
"""
Core evaluation execution pipeline for reward-kit.
Core evaluation execution pipeline for Eval Protocol.
This module orchestrates dataset loading, model response generation (optional),
and evaluation using specified reward functions.
"""
Expand Down
6 changes: 3 additions & 3 deletions eval_protocol/gcp_tools.py
Original file line number Diff line number Diff line change
Expand Up @@ -289,7 +289,7 @@ def ensure_artifact_registry_repo_exists(project_id: str, region: str, repo_name
"--location",
region,
"--description",
"Repository for reward-kit evaluators (auto-created by reward-kit CLI)",
"Repository for Eval Protocol evaluators (auto-created by Eval Protocol CLI)",
]
create_success, create_stdout, create_stderr = _run_gcloud_command(create_cmd, dry_run=dry_run)
if create_success:
Expand Down Expand Up @@ -442,7 +442,7 @@ def ensure_gcp_secret(
dummy_dockerfile = 'FROM python:3.10-slim\nCMD ["echo", "hello"]'
img_name = "gcr.io/my-test-project/my-test-reward-eval:latest" # Old GCR name, update for AR
# Example AR image name: us-central1-docker.pkg.dev/my-test-project/my-ar-repo/my-test-reward-eval:latest
ar_img_name = "us-central1-docker.pkg.dev/my-test-project/reward-kit-images/my-test-reward-eval:latest"
ar_img_name = "us-central1-docker.pkg.dev/my-test-project/eval-protocol-images/my-test-reward-eval:latest"

print(f"\n1. Simulating build and push for {ar_img_name} (dry_run=True)")
build_and_push_docker_image(
Expand Down Expand Up @@ -478,7 +478,7 @@ def ensure_gcp_secret(
project_id="my-test-project",
secret_id="my-test-api-key-secret",
secret_value="supersecretvalue123",
labels={"managed-by": "reward-kit-test"},
labels={"managed-by": "eval-protocol-test"},
dry_run=True,
)
print("\nNote: These are placeholder executions. Real implementation requires gcloud CLI and Docker.")
2 changes: 1 addition & 1 deletion eval_protocol/mcp_agent/config.py
Original file line number Diff line number Diff line change
Expand Up @@ -114,7 +114,7 @@ def model_post_init(self, __context: Any) -> None:


class AppConfig(BaseModel):
"""Root configuration for the RewardKit Intermediary MCP Server."""
"""Root configuration for the Eval Protocol Intermediary MCP Server."""

backends: List[BackendServerConfig] = Field(
default_factory=list,
Expand Down
2 changes: 1 addition & 1 deletion eval_protocol/mcp_env.py
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
"""
MCP Environment API for reward-kit - Backward Compatibility Facade
MCP Environment API for Eval Protocol - Backward Compatibility Facade

This module has been refactored into modular components for better maintainability.
This file now serves as a backward compatibility facade.
Expand Down
2 changes: 1 addition & 1 deletion mypy.ini
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ follow_imports = skip

# Specific package options
[mypy.eval_protocol.*]
# Be less strict when type checking reward kit code
# Be less strict when type checking Eval Protocol code
disallow_untyped_defs = False
disallow_incomplete_defs = False

Expand Down