decompressed-cli 0.1.0__tar.gz → 0.1.1__tar.gz

{decompressed_cli-0.1.0 → decompressed_cli-0.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: decompressed-cli
-Version: 0.1.0
+Version: 0.1.1
 Summary: CLI for Decompressed - Git-like version control for vector datasets
 Author-email: Decompressed <support@decompressed.io>
 License: MIT

{decompressed_cli-0.1.0 → decompressed_cli-0.1.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "decompressed-cli"
-version = "0.1.0"
+version = "0.1.1"
 description = "CLI for Decompressed - Git-like version control for vector datasets"
 readme = "README.md"
 requires-python = ">=3.9"

decompressed_cli-0.1.1/src/decompressed_cli/commands/imports_cmd.py

@@ -0,0 +1,220 @@
+"""Import commands for pulling vectors from external databases."""
+
+import time
+import typer
+from rich.console import Console
+from rich.table import Table
+from rich.panel import Panel
+from rich.progress import Progress, SpinnerColumn, TextColumn, BarColumn
+
+from ..config import get_client
+
+app = typer.Typer(no_args_is_help=True)
+console = Console()
+
+
+@app.command("pull")
+def pull(
+    connector: str = typer.Argument(..., help="Connector name or ID to import from"),
+    dataset_name: str = typer.Argument(..., help="Name for the new dataset"),
+    project: str = typer.Option(None, "--project", "-p", help="Project name or ID"),
+    no_metadata: bool = typer.Option(False, "--no-metadata", help="Skip importing metadata"),
+    batch_size: int = typer.Option(100, "--batch-size", "-b", help="Vectors per batch"),
+    no_wait: bool = typer.Option(False, "--no-wait", help="Don't wait for completion"),
+):
+    """
+    Pull vectors from an external database into a new dataset.
+    
+    Example:
+        dcp imports pull pinecone-prod my-backup
+        dcp imports pull qdrant-index imported-vectors --project ml-team
+    """
+    try:
+        client = get_client()
+        
+        console.print(f"[cyan]Connecting to connector:[/cyan] {connector}")
+        
+        # Initialize import
+        session = client.imports.init(
+            connector_id=connector,
+            dataset_name=dataset_name,
+            project=project,
+            include_metadata=not no_metadata,
+            batch_size=batch_size,
+        )
+        
+        console.print(Panel(
+            f"[green]✓[/green] Connected to [cyan]{session.connector_type}[/cyan]\n"
+            f"[dim]Estimated vectors:[/dim] {session.estimated_vectors:,}\n"
+            f"[dim]Dimension:[/dim] {session.dimension}\n"
+            f"[dim]Dataset ID:[/dim] {session.dataset_id}",
+            title="Import Initialized",
+            border_style="green"
+        ))
+        
+        # Start the import
+        result = client.imports.start(session.import_session_id)
+        console.print(f"[cyan]Import job started:[/cyan] {result.job_id[:8]}...")
+        
+        if no_wait:
+            console.print(f"\n[yellow]Import running in background.[/yellow]")
+            console.print(f"Check status: [cyan]dcp imports status {session.import_session_id}[/cyan]")
+            return
+        
+        # Wait with progress
+        with Progress(
+            SpinnerColumn(),
+            TextColumn("[progress.description]{task.description}"),
+            BarColumn(),
+            TextColumn("[progress.percentage]{task.percentage:>3.0f}%"),
+            console=console,
+        ) as progress:
+            task = progress.add_task("Importing vectors...", total=100)
+            
+            while True:
+                job = client.imports.status(session.import_session_id)
+                
+                if job.progress:
+                    progress.update(task, completed=job.progress)
+                
+                if job.status == "completed":
+                    progress.update(task, completed=100)
+                    break
+                elif job.status == "failed":
+                    console.print(f"\n[red]✗ Import failed:[/red] {job.error_message}")
+                    raise typer.Exit(1)
+                
+                time.sleep(2)
+        
+        console.print(Panel(
+            f"[green]✓[/green] Import complete!\n"
+            f"[dim]Dataset:[/dim] {dataset_name}\n"
+            f"[dim]Dataset ID:[/dim] {session.dataset_id}",
+            title="Success",
+            border_style="green"
+        ))
+        
+    except ValueError as e:
+        console.print(f"[red]Error:[/red] {e}")
+        raise typer.Exit(1)
+    except Exception as e:
+        console.print(f"[red]Error:[/red] {e}")
+        raise typer.Exit(1)
+
+
+@app.command("append")
+def append(
+    connector: str = typer.Argument(..., help="Connector name or ID to import from"),
+    dataset: str = typer.Argument(..., help="Existing dataset name or ID to append to"),
+    no_metadata: bool = typer.Option(False, "--no-metadata", help="Skip importing metadata"),
+    batch_size: int = typer.Option(100, "--batch-size", "-b", help="Vectors per batch"),
+    no_wait: bool = typer.Option(False, "--no-wait", help="Don't wait for completion"),
+):
+    """
+    Append vectors from an external database to an existing dataset.
+    
+    Example:
+        dcp imports append pinecone-prod my-dataset
+    """
+    try:
+        client = get_client()
+        
+        # Resolve dataset ID
+        ds = client.datasets.get(dataset)
+        
+        console.print(f"[cyan]Connecting to connector:[/cyan] {connector}")
+        console.print(f"[cyan]Appending to dataset:[/cyan] {ds.name} (v{ds.current_version})")
+        
+        # Initialize append import
+        session = client.imports.init_append(
+            connector_id=connector,
+            dataset_id=ds.id,
+            include_metadata=not no_metadata,
+            batch_size=batch_size,
+        )
+        
+        console.print(Panel(
+            f"[green]✓[/green] Connected to [cyan]{session.connector_type}[/cyan]\n"
+            f"[dim]Estimated vectors:[/dim] {session.estimated_vectors:,}\n"
+            f"[dim]Dimension:[/dim] {session.dimension}",
+            title="Append Import Initialized",
+            border_style="green"
+        ))
+        
+        # Start the import
+        result = client.imports.start(session.import_session_id)
+        console.print(f"[cyan]Import job started:[/cyan] {result.job_id[:8]}...")
+        
+        if no_wait:
+            console.print(f"\n[yellow]Import running in background.[/yellow]")
+            console.print(f"Check status: [cyan]dcp imports status {session.import_session_id}[/cyan]")
+            return
+        
+        # Wait with progress
+        with Progress(
+            SpinnerColumn(),
+            TextColumn("[progress.description]{task.description}"),
+            BarColumn(),
+            TextColumn("[progress.percentage]{task.percentage:>3.0f}%"),
+            console=console,
+        ) as progress:
+            task = progress.add_task("Importing vectors...", total=100)
+            
+            while True:
+                job = client.imports.status(session.import_session_id)
+                
+                if job.progress:
+                    progress.update(task, completed=job.progress)
+                
+                if job.status == "completed":
+                    progress.update(task, completed=100)
+                    break
+                elif job.status == "failed":
+                    console.print(f"\n[red]✗ Import failed:[/red] {job.error_message}")
+                    raise typer.Exit(1)
+                
+                time.sleep(2)
+        
+        console.print(f"[green]✓[/green] Appended vectors to [cyan]{ds.name}[/cyan]")
+        
+    except ValueError as e:
+        console.print(f"[red]Error:[/red] {e}")
+        raise typer.Exit(1)
+    except Exception as e:
+        console.print(f"[red]Error:[/red] {e}")
+        raise typer.Exit(1)
+
+
+@app.command("status")
+def status(
+    session_id: str = typer.Argument(..., help="Import session ID"),
+):
+    """Check status of an import job."""
+    try:
+        client = get_client()
+        job = client.imports.status(session_id)
+        
+        status_color = {
+            "initialized": "yellow",
+            "in_progress": "cyan",
+            "completed": "green",
+            "failed": "red",
+        }.get(job.status, "white")
+        
+        panel_content = f"""[cyan]Session ID:[/cyan] {job.import_session_id}
+[cyan]Dataset ID:[/cyan] {job.dataset_id or 'N/A'}
+[cyan]Status:[/cyan] [{status_color}]{job.status}[/{status_color}]
+[cyan]Progress:[/cyan] {job.progress or 0}%
+[cyan]Job ID:[/cyan] {job.job_id or 'N/A'}"""
+        
+        if job.error_message:
+            panel_content += f"\n[red]Error:[/red] {job.error_message}"
+        
+        console.print(Panel(panel_content, title="Import Status", border_style=status_color))
+        
+    except ValueError as e:
+        console.print(f"[red]Error:[/red] {e}")
+        raise typer.Exit(1)
+    except Exception as e:
+        console.print(f"[red]Error:[/red] {e}")
+        raise typer.Exit(1)

{decompressed_cli-0.1.0 → decompressed_cli-0.1.1}/src/decompressed_cli/main.py

@@ -4,7 +4,7 @@ import typer
 from rich.console import Console
 
 from . import __version__
-from .commands import config_cmd, datasets_cmd, versions_cmd, data_cmd
+from .commands import config_cmd, datasets_cmd, versions_cmd, data_cmd, imports_cmd
 
 app = typer.Typer(
     name="dcp",
@@ -17,6 +17,7 @@ console = Console()
 app.add_typer(config_cmd.app, name="config", help="Manage CLI configuration")
 app.add_typer(datasets_cmd.app, name="datasets", help="Manage datasets")
 app.add_typer(data_cmd.app, name="data", help="Pull/push data (alias)")
+app.add_typer(imports_cmd.app, name="imports", help="Import vectors from external databases")
 
 # Register top-level versioning commands
 app.command("log")(versions_cmd.log)

{decompressed_cli-0.1.0 → decompressed_cli-0.1.1}/src/decompressed_cli.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: decompressed-cli
-Version: 0.1.0
+Version: 0.1.1
 Summary: CLI for Decompressed - Git-like version control for vector datasets
 Author-email: Decompressed <support@decompressed.io>
 License: MIT

{decompressed_cli-0.1.0 → decompressed_cli-0.1.1}/src/decompressed_cli.egg-info/SOURCES.txt

@@ -13,4 +13,5 @@ src/decompressed_cli/commands/__init__.py
 src/decompressed_cli/commands/config_cmd.py
 src/decompressed_cli/commands/data_cmd.py
 src/decompressed_cli/commands/datasets_cmd.py
+src/decompressed_cli/commands/imports_cmd.py
 src/decompressed_cli/commands/versions_cmd.py