sference-cli 0.1.4__tar.gz → 0.1.6__tar.gz

{sference_cli-0.1.4 → sference_cli-0.1.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sference-cli
-Version: 0.1.4
+Version: 0.1.6
 Summary: sference command-line interface
 Project-URL: Homepage, https://sference.com
 Project-URL: Repository, https://github.com/s-ference/sference
@@ -21,7 +21,7 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Utilities
 Requires-Python: >=3.10
-Requires-Dist: sference-sdk>=0.1.4
+Requires-Dist: sference-sdk>=0.1.6
 Requires-Dist: typer>=0.24.1
 Description-Content-Type: text/markdown
 
@@ -148,7 +148,7 @@ Requires the [Pi CLI](https://pi.dev/docs) on `PATH`. Writes a `sference` provid
 | Command | Description |
 |---------|-------------|
 | `sference batch list` | List batches (table; `--json` for raw payload) |
-| `sference batch submit` | Submit a JSONL file (`--input-file`, optional `--model` for content-only lines, `--window` `15m`/`1h`/`24h`) |
+| `sference batch submit` | Submit a JSONL file (`--input-file`, optional `--model` for content-only lines, `--window` `24h`) |
 | `sference batch stream` | Submit, wait, print **JSONL results on stdout** (see below) |
 | `sference batch status` | Get one batch (`--batch-id`, `--json`) |
 | `sference batch wait` | Poll until terminal state (`--batch-id`, `--poll-interval`, `--timeout`, `--json`) |
@@ -170,7 +170,7 @@ Long-lived **streams** are separate from **batches**: you create a stream, submi
 
 | Command | Description |
 |---------|-------------|
-| `sference stream create` | Create a stream (`--name`, `--window` `15m`/`1h`/`24h`, `--json`) |
+| `sference stream create` | Create a stream (`--name`, `--window` `24h`, `--json`) |
 | `sference stream list` | List streams (`--json`) |
 | `sference stream status` | Full detail + counters (`--stream-id`, `--json`) |
 | `sference stream submit` | Create responses from JSONL via `POST /v1/responses` per line (`metadata.stream_id` set automatically; `--stream-id`, `--input-file`, `--model` required for content-only lines) — per line: OpenAI batch-style `{custom_id?, method, url, body}` or content-only `{content}` |

{sference_cli-0.1.4 → sference_cli-0.1.6}/README.md

@@ -121,7 +121,7 @@ Requires the [Pi CLI](https://pi.dev/docs) on `PATH`. Writes a `sference` provid
 | Command | Description |
 |---------|-------------|
 | `sference batch list` | List batches (table; `--json` for raw payload) |
-| `sference batch submit` | Submit a JSONL file (`--input-file`, optional `--model` for content-only lines, `--window` `15m`/`1h`/`24h`) |
+| `sference batch submit` | Submit a JSONL file (`--input-file`, optional `--model` for content-only lines, `--window` `24h`) |
 | `sference batch stream` | Submit, wait, print **JSONL results on stdout** (see below) |
 | `sference batch status` | Get one batch (`--batch-id`, `--json`) |
 | `sference batch wait` | Poll until terminal state (`--batch-id`, `--poll-interval`, `--timeout`, `--json`) |
@@ -143,7 +143,7 @@ Long-lived **streams** are separate from **batches**: you create a stream, submi
 
 | Command | Description |
 |---------|-------------|
-| `sference stream create` | Create a stream (`--name`, `--window` `15m`/`1h`/`24h`, `--json`) |
+| `sference stream create` | Create a stream (`--name`, `--window` `24h`, `--json`) |
 | `sference stream list` | List streams (`--json`) |
 | `sference stream status` | Full detail + counters (`--stream-id`, `--json`) |
 | `sference stream submit` | Create responses from JSONL via `POST /v1/responses` per line (`metadata.stream_id` set automatically; `--stream-id`, `--input-file`, `--model` required for content-only lines) — per line: OpenAI batch-style `{custom_id?, method, url, body}` or content-only `{content}` |

{sference_cli-0.1.4 → sference_cli-0.1.6}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "sference-cli"
-version = "0.1.4"
+version = "0.1.6"
 description = "sference command-line interface"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -23,7 +23,7 @@ classifiers = [
 ]
 dependencies = [
     "typer>=0.24.1",
-    "sference-sdk>=0.1.4",
+    "sference-sdk>=0.1.6",
 ]
 
 [project.urls]

{sference_cli-0.1.4 → sference_cli-0.1.6}/sference_cli/main.py

@@ -32,11 +32,13 @@ batch_app = typer.Typer(help="Batch commands", invoke_without_command=True)
 stream_app = typer.Typer(help="Stream commands", invoke_without_command=True)
 responses_app = typer.Typer(help="Responses commands", invoke_without_command=True)
 models_app = typer.Typer(help="List models (GET /v1/models)", invoke_without_command=True)
+embeddings_app = typer.Typer(help="Embeddings commands", invoke_without_command=True)
 app.add_typer(auth_app, name="auth")
 app.add_typer(batch_app, name="batch")
 app.add_typer(stream_app, name="stream")
 app.add_typer(responses_app, name="responses")
 app.add_typer(models_app, name="models")
+app.add_typer(embeddings_app, name="embeddings")
 register_launch_commands(app)
 
 CREDENTIALS_PATH = Path.home() / ".sference" / "credentials.json"
@@ -163,6 +165,14 @@ def _capability_flag(caps: object, key: str) -> str:
     return "—"
 
 
+def _modality_label(raw: object) -> str:
+    if not isinstance(raw, str) or not raw:
+        return "—"
+    if raw.startswith("text_"):
+        return raw.removeprefix("text_")
+    return raw
+
+
 def _print_models_table(payload: object) -> None:
     if not isinstance(payload, dict):
         typer.echo(str(payload))
@@ -175,9 +185,9 @@ def _print_models_table(payload: object) -> None:
         typer.echo("No models.")
         return
 
-    w_id, w_name, w_ctx, w_vis, w_pdf, w_think, w_tools = 34, 18, 8, 6, 4, 8, 5
+    w_id, w_name, w_mod, w_ctx, w_vis, w_pdf, w_think, w_tools = 34, 18, 10, 8, 6, 4, 8, 5
     typer.echo(
-        f"{'id':<{w_id}} {'display_name':<{w_name}} {'context':>{w_ctx}} "
+        f"{'id':<{w_id}} {'display_name':<{w_name}} {'modality':<{w_mod}} {'context':>{w_ctx}} "
         f"{'vision':>{w_vis}} {'pdf':>{w_pdf}} {'thinking':>{w_think}} {'tools':>{w_tools}}"
     )
     for row in rows:
@@ -189,6 +199,9 @@ def _print_models_table(payload: object) -> None:
         display_name = str(row.get("display_name") or "")
         if len(display_name) > w_name:
             display_name = display_name[: w_name - 1] + "…"
+        modality = _modality_label(row.get("modality"))
+        if len(modality) > w_mod:
+            modality = modality[: w_mod - 1] + "…"
         ctx_raw = row.get("context_tokens")
         context = str(ctx_raw) if isinstance(ctx_raw, int) else "—"
         caps = row.get("capabilities")
@@ -197,7 +210,7 @@ def _print_models_table(payload: object) -> None:
         thinking = _capability_flag(caps, "thinking")
         tools = _capability_flag(caps, "tools")
         typer.echo(
-            f"{model_id:<{w_id}} {display_name:<{w_name}} {context:>{w_ctx}} "
+            f"{model_id:<{w_id}} {display_name:<{w_name}} {modality:<{w_mod}} {context:>{w_ctx}} "
             f"{vision:>{w_vis}} {pdf:>{w_pdf}} {thinking:>{w_think}} {tools:>{w_tools}}"
         )
 
@@ -286,6 +299,34 @@ def models_list(
     _list_models(client=client, as_json=as_json)
 
 
+@embeddings_app.command("create")
+def embeddings_create(
+    model: str = typer.Option(..., "--model"),
+    input_text: list[str] = typer.Option(..., "--input", help="Text to embed (repeat for multiple strings)."),
+    encoding_format: str = typer.Option("float", "--encoding-format", help='"float" or "base64".'),
+    dimensions: int | None = typer.Option(None, "--dimensions"),
+    timeout: float = typer.Option(600.0, "--timeout", help="HTTP read timeout in seconds."),
+    base_url: str = typer.Option("https://api.sference.com"),
+    as_json: bool = typer.Option(False, "--json"),
+) -> None:
+    """Create embeddings (POST /v1/embeddings)."""
+    _ensure_api_credential()
+    if encoding_format not in ("float", "base64"):
+        typer.echo('encoding_format must be "float" or "base64".', err=True)
+        raise typer.Exit(code=1)
+    inp: str | list[str] = input_text[0] if len(input_text) == 1 else input_text
+    client = _client(base_url, timeout=timeout)
+    resp = _call_api(
+        lambda: client.create_embeddings(
+            model=model,
+            input=inp,
+            encoding_format=encoding_format,  # type: ignore[arg-type]
+            dimensions=dimensions,
+        )
+    )
+    _print(resp.model_dump(), as_json or True)
+
+
 @auth_app.command("login")
 def auth_login(
     api_key: Optional[str] = typer.Option(
@@ -434,7 +475,7 @@ def responses_result(
             resp = _call_api(lambda: client.get_response(id))
             d = resp.model_dump()
             status = d.get("status") if isinstance(d, dict) else None
-            if status in ("completed", "failed", "cancelled"):
+            if status in ("completed", "failed", "cancelled", "incomplete"):
                 _print(d, True)
                 return
             time.sleep(max(0.01, poll_interval))
@@ -552,7 +593,7 @@ def batch_submit(
     window: str = typer.Option(
         "24h",
         "--window",
-        help='Batch SLA window: "15m", "1h", or "24h".',
+        help='Batch SLA window: "24h" is the only supported value.',
         callback=_window_choice,
     ),
     base_url: str = typer.Option("https://api.sference.com"),
@@ -583,7 +624,7 @@ def batch_stream(
     window: str = typer.Option(
         "24h",
         "--window",
-        help='Batch SLA window: "15m", "1h", or "24h".',
+        help='Batch SLA window: "24h" is the only supported value.',
         callback=_window_choice,
     ),
     poll_interval: float = typer.Option(2.0, "--poll-interval", help="Seconds between status polls while the batch is running."),
@@ -699,7 +740,7 @@ def stream_create(
     window: str = typer.Option(
         "24h",
         "--window",
-        help='Per-item SLA window: "15m", "1h", or "24h" (default for items in this stream).',
+        help='Per-item SLA window: "24h" is the only supported value.',
         callback=_window_choice,
     ),
     base_url: str = typer.Option("https://api.sference.com"),