mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-02-05 01:50:27 +08:00
feat: Add reranker model management commands and UI integration
- Implemented CLI commands for listing, downloading, deleting, and retrieving information about reranker models. - Enhanced the dashboard UI to support embedding and reranker configurations with internationalization. - Updated environment variable management for embedding and reranker settings. - Added functionality to dynamically update model options based on selected backend. - Improved user experience with status indicators and action buttons for model management. - Integrated new reranker models with detailed metadata and recommendations.
This commit is contained in:
catlog22
@@ -1975,6 +1975,175 @@ def model_info(
|
||||
console.print(f" Use case: {data['use_case']}")
|
||||
|
||||
|
||||
# ==================== Reranker Model Management Commands ====================
|
||||
|
||||
|
||||
@app.command(name="reranker-model-list")
|
||||
def reranker_model_list(
|
||||
json_mode: bool = typer.Option(False, "--json", help="Output JSON response."),
|
||||
) -> None:
|
||||
"""List available reranker models and their installation status.
|
||||
|
||||
Shows reranker model profiles with:
|
||||
- Installation status
|
||||
- Model size
|
||||
- Use case recommendations
|
||||
"""
|
||||
try:
|
||||
from codexlens.cli.model_manager import list_reranker_models
|
||||
|
||||
result = list_reranker_models()
|
||||
|
||||
if json_mode:
|
||||
print_json(**result)
|
||||
else:
|
||||
if not result["success"]:
|
||||
console.print(f"[red]Error:[/red] {result.get('error', 'Unknown error')}")
|
||||
raise typer.Exit(code=1)
|
||||
|
||||
data = result["result"]
|
||||
models = data["models"]
|
||||
cache_dir = data["cache_dir"]
|
||||
cache_exists = data["cache_exists"]
|
||||
|
||||
console.print("[bold]Available Reranker Models:[/bold]")
|
||||
console.print(f"Cache directory: [dim]{cache_dir}[/dim] {'(exists)' if cache_exists else '(not found)'}\n")
|
||||
|
||||
table = Table(show_header=True, header_style="bold")
|
||||
table.add_column("Profile", style="cyan")
|
||||
table.add_column("Model", style="dim")
|
||||
table.add_column("Size", justify="right")
|
||||
table.add_column("Status")
|
||||
table.add_column("Description")
|
||||
|
||||
for m in models:
|
||||
status = "[green]✓ Installed[/green]" if m["installed"] else "[dim]Not installed[/dim]"
|
||||
size = f"{m['actual_size_mb']:.1f} MB" if m["installed"] and m["actual_size_mb"] else f"~{m['estimated_size_mb']} MB"
|
||||
rec = " [yellow]★[/yellow]" if m.get("recommended") else ""
|
||||
table.add_row(m["profile"] + rec, m["model_name"], size, status, m["description"])
|
||||
|
||||
console.print(table)
|
||||
console.print("\n[yellow]★[/yellow] = Recommended")
|
||||
|
||||
except ImportError:
|
||||
if json_mode:
|
||||
print_json(success=False, error="fastembed reranker not available. Install with: pip install fastembed>=0.4.0")
|
||||
else:
|
||||
console.print("[red]Error:[/red] fastembed reranker not available")
|
||||
console.print("Install with: [cyan]pip install fastembed>=0.4.0[/cyan]")
|
||||
raise typer.Exit(code=1)
|
||||
|
||||
|
||||
@app.command(name="reranker-model-download")
|
||||
def reranker_model_download(
|
||||
profile: str = typer.Argument(..., help="Reranker model profile to download."),
|
||||
json_mode: bool = typer.Option(False, "--json", help="Output JSON response."),
|
||||
) -> None:
|
||||
"""Download a reranker model by profile name.
|
||||
|
||||
Example:
|
||||
codexlens reranker-model-download ms-marco-mini # Download default reranker
|
||||
"""
|
||||
try:
|
||||
from codexlens.cli.model_manager import download_reranker_model
|
||||
|
||||
if not json_mode:
|
||||
console.print(f"[bold]Downloading reranker model:[/bold] {profile}")
|
||||
console.print("[dim]This may take a few minutes depending on your internet connection...[/dim]\n")
|
||||
|
||||
progress_callback = None if json_mode else lambda msg: console.print(f"[cyan]{msg}[/cyan]")
|
||||
|
||||
result = download_reranker_model(profile, progress_callback=progress_callback)
|
||||
|
||||
if json_mode:
|
||||
print_json(**result)
|
||||
else:
|
||||
if not result["success"]:
|
||||
console.print(f"[red]Error:[/red] {result.get('error', 'Unknown error')}")
|
||||
raise typer.Exit(code=1)
|
||||
|
||||
data = result["result"]
|
||||
console.print(f"[green]✓[/green] Reranker model downloaded successfully!")
|
||||
console.print(f" Profile: {data['profile']}")
|
||||
console.print(f" Model: {data['model_name']}")
|
||||
console.print(f" Cache size: {data['cache_size_mb']:.1f} MB")
|
||||
console.print(f" Location: [dim]{data['cache_path']}[/dim]")
|
||||
|
||||
except ImportError:
|
||||
if json_mode:
|
||||
print_json(success=False, error="fastembed reranker not available. Install with: pip install fastembed>=0.4.0")
|
||||
else:
|
||||
console.print("[red]Error:[/red] fastembed reranker not available")
|
||||
console.print("Install with: [cyan]pip install fastembed>=0.4.0[/cyan]")
|
||||
raise typer.Exit(code=1)
|
||||
|
||||
|
||||
@app.command(name="reranker-model-delete")
|
||||
def reranker_model_delete(
|
||||
profile: str = typer.Argument(..., help="Reranker model profile to delete."),
|
||||
json_mode: bool = typer.Option(False, "--json", help="Output JSON response."),
|
||||
) -> None:
|
||||
"""Delete a downloaded reranker model from cache.
|
||||
|
||||
Example:
|
||||
codexlens reranker-model-delete ms-marco-mini # Delete reranker model
|
||||
"""
|
||||
from codexlens.cli.model_manager import delete_reranker_model
|
||||
|
||||
if not json_mode:
|
||||
console.print(f"[bold yellow]Deleting reranker model:[/bold yellow] {profile}")
|
||||
|
||||
result = delete_reranker_model(profile)
|
||||
|
||||
if json_mode:
|
||||
print_json(**result)
|
||||
else:
|
||||
if not result["success"]:
|
||||
console.print(f"[red]Error:[/red] {result.get('error', 'Unknown error')}")
|
||||
raise typer.Exit(code=1)
|
||||
|
||||
data = result["result"]
|
||||
console.print(f"[green]✓[/green] Reranker model deleted successfully!")
|
||||
console.print(f" Profile: {data['profile']}")
|
||||
console.print(f" Model: {data['model_name']}")
|
||||
console.print(f" Freed space: {data['deleted_size_mb']:.1f} MB")
|
||||
|
||||
|
||||
@app.command(name="reranker-model-info")
|
||||
def reranker_model_info(
|
||||
profile: str = typer.Argument(..., help="Reranker model profile to get info."),
|
||||
json_mode: bool = typer.Option(False, "--json", help="Output JSON response."),
|
||||
) -> None:
|
||||
"""Get detailed information about a reranker model profile.
|
||||
|
||||
Example:
|
||||
codexlens reranker-model-info ms-marco-mini # Get reranker model details
|
||||
"""
|
||||
from codexlens.cli.model_manager import get_reranker_model_info
|
||||
|
||||
result = get_reranker_model_info(profile)
|
||||
|
||||
if json_mode:
|
||||
print_json(**result)
|
||||
else:
|
||||
if not result["success"]:
|
||||
console.print(f"[red]Error:[/red] {result.get('error', 'Unknown error')}")
|
||||
raise typer.Exit(code=1)
|
||||
|
||||
data = result["result"]
|
||||
console.print(f"[bold]Reranker Model Profile:[/bold] {data['profile']}")
|
||||
console.print(f" Model name: {data['model_name']}")
|
||||
console.print(f" Status: {'[green]Installed[/green]' if data['installed'] else '[dim]Not installed[/dim]'}")
|
||||
if data['installed'] and data['actual_size_mb']:
|
||||
console.print(f" Cache size: {data['actual_size_mb']:.1f} MB")
|
||||
console.print(f" Location: [dim]{data['cache_path']}[/dim]")
|
||||
else:
|
||||
console.print(f" Estimated size: ~{data['estimated_size_mb']} MB")
|
||||
console.print(f" Recommended: {'[green]Yes[/green]' if data.get('recommended') else '[dim]No[/dim]'}")
|
||||
console.print(f"\n Description: {data['description']}")
|
||||
console.print(f" Use case: {data['use_case']}")
|
||||
|
||||
|
||||
# ==================== Embedding Management Commands ====================
|
||||
|
||||
@app.command(name="embeddings-status", hidden=True, deprecated=True)
|
||||
|
||||
@@ -12,6 +12,66 @@ try:
|
||||
except ImportError:
|
||||
FASTEMBED_AVAILABLE = False
|
||||
|
||||
try:
|
||||
from fastembed import TextCrossEncoder
|
||||
RERANKER_AVAILABLE = True
|
||||
except ImportError:
|
||||
RERANKER_AVAILABLE = False
|
||||
|
||||
|
||||
# Reranker model profiles with metadata
|
||||
# Note: fastembed TextCrossEncoder uses ONNX models from HuggingFace
|
||||
RERANKER_MODEL_PROFILES = {
|
||||
"ms-marco-mini": {
|
||||
"model_name": "Xenova/ms-marco-MiniLM-L-6-v2",
|
||||
"cache_name": "Xenova/ms-marco-MiniLM-L-6-v2",
|
||||
"size_mb": 90,
|
||||
"description": "Fast, lightweight reranker (default)",
|
||||
"use_case": "Quick prototyping, resource-constrained environments",
|
||||
"recommended": True,
|
||||
},
|
||||
"ms-marco-12": {
|
||||
"model_name": "Xenova/ms-marco-MiniLM-L-12-v2",
|
||||
"cache_name": "Xenova/ms-marco-MiniLM-L-12-v2",
|
||||
"size_mb": 130,
|
||||
"description": "Better quality, 12-layer MiniLM",
|
||||
"use_case": "General purpose reranking with better accuracy",
|
||||
"recommended": True,
|
||||
},
|
||||
"bge-base": {
|
||||
"model_name": "BAAI/bge-reranker-base",
|
||||
"cache_name": "BAAI/bge-reranker-base",
|
||||
"size_mb": 280,
|
||||
"description": "BGE reranker base model",
|
||||
"use_case": "High-quality reranking for production",
|
||||
"recommended": True,
|
||||
},
|
||||
"bge-large": {
|
||||
"model_name": "BAAI/bge-reranker-large",
|
||||
"cache_name": "BAAI/bge-reranker-large",
|
||||
"size_mb": 560,
|
||||
"description": "BGE reranker large model (high resource usage)",
|
||||
"use_case": "Maximum quality reranking",
|
||||
"recommended": False,
|
||||
},
|
||||
"jina-tiny": {
|
||||
"model_name": "jinaai/jina-reranker-v1-tiny-en",
|
||||
"cache_name": "jinaai/jina-reranker-v1-tiny-en",
|
||||
"size_mb": 70,
|
||||
"description": "Jina tiny reranker, very fast",
|
||||
"use_case": "Ultra-low latency applications",
|
||||
"recommended": True,
|
||||
},
|
||||
"jina-turbo": {
|
||||
"model_name": "jinaai/jina-reranker-v1-turbo-en",
|
||||
"cache_name": "jinaai/jina-reranker-v1-turbo-en",
|
||||
"size_mb": 150,
|
||||
"description": "Jina turbo reranker, balanced",
|
||||
"use_case": "Fast reranking with good accuracy",
|
||||
"recommended": True,
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
# Model profiles with metadata
|
||||
# Note: 768d is max recommended dimension for optimal performance/quality balance
|
||||
@@ -348,3 +408,235 @@ def get_model_info(profile: str) -> Dict[str, any]:
|
||||
"cache_path": str(model_cache_path) if installed else None,
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
# ============================================================================
|
||||
# Reranker Model Management Functions
|
||||
# ============================================================================
|
||||
|
||||
|
||||
def list_reranker_models() -> Dict[str, any]:
|
||||
"""List available reranker model profiles and their installation status.
|
||||
|
||||
Returns:
|
||||
Dictionary with reranker model profiles, installed status, and cache info
|
||||
"""
|
||||
if not RERANKER_AVAILABLE:
|
||||
return {
|
||||
"success": False,
|
||||
"error": "fastembed reranker not available. Install with: pip install fastembed>=0.4.0",
|
||||
}
|
||||
|
||||
cache_dir = get_cache_dir()
|
||||
cache_exists = cache_dir.exists()
|
||||
|
||||
models = []
|
||||
for profile, info in RERANKER_MODEL_PROFILES.items():
|
||||
model_name = info["model_name"]
|
||||
|
||||
# Check if model is cached
|
||||
installed = False
|
||||
cache_size_mb = 0
|
||||
|
||||
if cache_exists:
|
||||
model_cache_path = _get_model_cache_path(cache_dir, info)
|
||||
if model_cache_path.exists():
|
||||
installed = True
|
||||
total_size = sum(
|
||||
f.stat().st_size
|
||||
for f in model_cache_path.rglob("*")
|
||||
if f.is_file()
|
||||
)
|
||||
cache_size_mb = round(total_size / (1024 * 1024), 1)
|
||||
|
||||
models.append({
|
||||
"profile": profile,
|
||||
"model_name": model_name,
|
||||
"estimated_size_mb": info["size_mb"],
|
||||
"actual_size_mb": cache_size_mb if installed else None,
|
||||
"description": info["description"],
|
||||
"use_case": info["use_case"],
|
||||
"installed": installed,
|
||||
"recommended": info.get("recommended", True),
|
||||
})
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"result": {
|
||||
"models": models,
|
||||
"cache_dir": str(cache_dir),
|
||||
"cache_exists": cache_exists,
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
def download_reranker_model(profile: str, progress_callback: Optional[callable] = None) -> Dict[str, any]:
|
||||
"""Download a reranker model by profile name.
|
||||
|
||||
Args:
|
||||
profile: Reranker model profile name
|
||||
progress_callback: Optional callback function to report progress
|
||||
|
||||
Returns:
|
||||
Result dictionary with success status
|
||||
"""
|
||||
if not RERANKER_AVAILABLE:
|
||||
return {
|
||||
"success": False,
|
||||
"error": "fastembed reranker not available. Install with: pip install fastembed>=0.4.0",
|
||||
}
|
||||
|
||||
if profile not in RERANKER_MODEL_PROFILES:
|
||||
return {
|
||||
"success": False,
|
||||
"error": f"Unknown reranker profile: {profile}. Available: {', '.join(RERANKER_MODEL_PROFILES.keys())}",
|
||||
}
|
||||
|
||||
info = RERANKER_MODEL_PROFILES[profile]
|
||||
model_name = info["model_name"]
|
||||
|
||||
try:
|
||||
cache_dir = get_cache_dir()
|
||||
|
||||
if progress_callback:
|
||||
progress_callback(f"Downloading reranker {model_name}...")
|
||||
|
||||
# Download model by instantiating TextCrossEncoder with explicit cache_dir
|
||||
reranker = TextCrossEncoder(model_name=model_name, cache_dir=str(cache_dir))
|
||||
|
||||
# Trigger actual download by calling rerank
|
||||
if progress_callback:
|
||||
progress_callback(f"Initializing {model_name}...")
|
||||
|
||||
list(reranker.rerank("test query", ["test document"]))
|
||||
|
||||
if progress_callback:
|
||||
progress_callback(f"Reranker {model_name} downloaded successfully")
|
||||
|
||||
# Get cache info
|
||||
model_cache_path = _get_model_cache_path(cache_dir, info)
|
||||
|
||||
cache_size = 0
|
||||
if model_cache_path.exists():
|
||||
total_size = sum(
|
||||
f.stat().st_size
|
||||
for f in model_cache_path.rglob("*")
|
||||
if f.is_file()
|
||||
)
|
||||
cache_size = round(total_size / (1024 * 1024), 1)
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"result": {
|
||||
"profile": profile,
|
||||
"model_name": model_name,
|
||||
"cache_size_mb": cache_size,
|
||||
"cache_path": str(model_cache_path),
|
||||
},
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
return {
|
||||
"success": False,
|
||||
"error": f"Failed to download reranker model: {str(e)}",
|
||||
}
|
||||
|
||||
|
||||
def delete_reranker_model(profile: str) -> Dict[str, any]:
|
||||
"""Delete a downloaded reranker model from cache.
|
||||
|
||||
Args:
|
||||
profile: Reranker model profile name to delete
|
||||
|
||||
Returns:
|
||||
Result dictionary with success status
|
||||
"""
|
||||
if profile not in RERANKER_MODEL_PROFILES:
|
||||
return {
|
||||
"success": False,
|
||||
"error": f"Unknown reranker profile: {profile}. Available: {', '.join(RERANKER_MODEL_PROFILES.keys())}",
|
||||
}
|
||||
|
||||
info = RERANKER_MODEL_PROFILES[profile]
|
||||
model_name = info["model_name"]
|
||||
cache_dir = get_cache_dir()
|
||||
model_cache_path = _get_model_cache_path(cache_dir, info)
|
||||
|
||||
if not model_cache_path.exists():
|
||||
return {
|
||||
"success": False,
|
||||
"error": f"Reranker model {profile} ({model_name}) is not installed",
|
||||
}
|
||||
|
||||
try:
|
||||
total_size = sum(
|
||||
f.stat().st_size
|
||||
for f in model_cache_path.rglob("*")
|
||||
if f.is_file()
|
||||
)
|
||||
size_mb = round(total_size / (1024 * 1024), 1)
|
||||
|
||||
shutil.rmtree(model_cache_path)
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"result": {
|
||||
"profile": profile,
|
||||
"model_name": model_name,
|
||||
"deleted_size_mb": size_mb,
|
||||
"cache_path": str(model_cache_path),
|
||||
},
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
return {
|
||||
"success": False,
|
||||
"error": f"Failed to delete reranker model: {str(e)}",
|
||||
}
|
||||
|
||||
|
||||
def get_reranker_model_info(profile: str) -> Dict[str, any]:
|
||||
"""Get detailed information about a reranker model profile.
|
||||
|
||||
Args:
|
||||
profile: Reranker model profile name
|
||||
|
||||
Returns:
|
||||
Result dictionary with model information
|
||||
"""
|
||||
if profile not in RERANKER_MODEL_PROFILES:
|
||||
return {
|
||||
"success": False,
|
||||
"error": f"Unknown reranker profile: {profile}. Available: {', '.join(RERANKER_MODEL_PROFILES.keys())}",
|
||||
}
|
||||
|
||||
info = RERANKER_MODEL_PROFILES[profile]
|
||||
model_name = info["model_name"]
|
||||
|
||||
cache_dir = get_cache_dir()
|
||||
model_cache_path = _get_model_cache_path(cache_dir, info)
|
||||
installed = model_cache_path.exists()
|
||||
|
||||
cache_size_mb = None
|
||||
if installed:
|
||||
total_size = sum(
|
||||
f.stat().st_size
|
||||
for f in model_cache_path.rglob("*")
|
||||
if f.is_file()
|
||||
)
|
||||
cache_size_mb = round(total_size / (1024 * 1024), 1)
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"result": {
|
||||
"profile": profile,
|
||||
"model_name": model_name,
|
||||
"estimated_size_mb": info["size_mb"],
|
||||
"actual_size_mb": cache_size_mb,
|
||||
"description": info["description"],
|
||||
"use_case": info["use_case"],
|
||||
"installed": installed,
|
||||
"recommended": info.get("recommended", True),
|
||||
"cache_path": str(model_cache_path) if installed else None,
|
||||
},
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user