vectorizer-sdk 3.0.0__tar.gz → 3.0.3__tar.gz

{vectorizer_sdk-3.0.0/vectorizer_sdk.egg-info → vectorizer_sdk-3.0.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: vectorizer_sdk
-Version: 3.0.0
+Version: 3.0.3
 Summary: Python SDK for Vectorizer - Semantic search, vector operations, and the VectorizerRPC binary transport (default in v3.x)
 Author-email: HiveLLM Team <team@hivellm.org>
 License: Apache-2.0

{vectorizer_sdk-3.0.0 → vectorizer_sdk-3.0.3}/pyproject.toml

@@ -1,110 +1,110 @@
-[build-system]
-requires = ["setuptools>=61.0", "wheel"]
-build-backend = "setuptools.build_meta"
-
-[project]
-name = "vectorizer_sdk"
-version = "3.0.0"
-description = "Python SDK for Vectorizer - Semantic search, vector operations, and the VectorizerRPC binary transport (default in v3.x)"
-readme = "README.md"
-requires-python = ">=3.8"
-license = {text = "Apache-2.0"}
-authors = [
-    {name = "HiveLLM Team", email = "team@hivellm.org"}
-]
-keywords = [
-    "vectorizer",
-    "semantic-search",
-    "embeddings",
-    "machine-learning",
-    "ai",
-    "search",
-    "vectors",
-    "similarity",
-    "hivellm",
-    "umicp"
-]
-classifiers = [
-    "Development Status :: 5 - Production/Stable",
-    "Intended Audience :: Developers",
-    "Operating System :: OS Independent",
-    "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.8",
-    "Programming Language :: Python :: 3.9",
-    "Programming Language :: Python :: 3.10",
-    "Programming Language :: Python :: 3.11",
-    "Programming Language :: Python :: 3.12",
-    "Topic :: Software Development :: Libraries :: Python Modules",
-    "Topic :: Scientific/Engineering :: Artificial Intelligence",
-    "Topic :: Text Processing :: Indexing",
-    "Topic :: Internet :: WWW/HTTP :: Dynamic Content",
-]
-
-dependencies = [
-    "aiohttp>=3.10.0",
-    "msgpack>=1.1.0",
-]
-
-[project.optional-dependencies]
-umicp = [
-    "umicp-python>=0.1.3",
-]
-dev = [
-    "pytest>=8.0.0",
-    "pytest-asyncio>=0.24.0",
-    "pytest-cov>=5.0.0",
-    "black>=25.0.0",
-    "isort>=5.13.0",
-    "flake8>=7.0.0",
-    "mypy>=1.11.0",
-    "pre-commit>=4.0.0",
-]
-docs = [
-    "sphinx>=7.0.0",
-    "sphinx-rtd-theme>=2.0.0",
-    "myst-parser>=3.0.0",
-]
-test = [
-    "pytest>=8.0.0",
-    "pytest-asyncio>=0.24.0",
-    "pytest-cov>=5.0.0",
-    "httpx>=0.27.0",
-]
-
-[project.urls]
-Homepage = "https://github.com/hivellm/vectorizer"
-Documentation = "https://github.com/hivellm/vectorizer/tree/main/docs"
-Repository = "https://github.com/hivellm/vectorizer"
-Issues = "https://github.com/hivellm/vectorizer/issues"
-
-[project.scripts]
-vectorizer-cli = "cli:main"
-
-[tool.setuptools.packages.find]
-include = ["*"]
-exclude = ["tests*", "examples*", "docs*"]
-
-[tool.setuptools.package-data]
-"*" = ["py.typed"]
-
-[tool.pytest.ini_options]
-asyncio_mode = "auto"
-testpaths = ["tests"]
-python_files = ["test_*.py"]
-python_classes = ["Test*"]
-python_functions = ["test_*"]
-
-[tool.black]
-line-length = 100
-target-version = ['py38', 'py39', 'py310', 'py311', 'py312']
-
-[tool.isort]
-profile = "black"
-line_length = 100
-
-[tool.mypy]
-python_version = "3.8"
-warn_return_any = true
-warn_unused_configs = true
-disallow_untyped_defs = false
-
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "vectorizer_sdk"
+version = "3.0.3"
+description = "Python SDK for Vectorizer - Semantic search, vector operations, and the VectorizerRPC binary transport (default in v3.x)"
+readme = "README.md"
+requires-python = ">=3.8"
+license = {text = "Apache-2.0"}
+authors = [
+    {name = "HiveLLM Team", email = "team@hivellm.org"}
+]
+keywords = [
+    "vectorizer",
+    "semantic-search",
+    "embeddings",
+    "machine-learning",
+    "ai",
+    "search",
+    "vectors",
+    "similarity",
+    "hivellm",
+    "umicp"
+]
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Developers",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Text Processing :: Indexing",
+    "Topic :: Internet :: WWW/HTTP :: Dynamic Content",
+]
+
+dependencies = [
+    "aiohttp>=3.10.0",
+    "msgpack>=1.1.0",
+]
+
+[project.optional-dependencies]
+umicp = [
+    "umicp-python>=0.1.3",
+]
+dev = [
+    "pytest>=8.0.0",
+    "pytest-asyncio>=0.24.0",
+    "pytest-cov>=5.0.0",
+    "black>=25.0.0",
+    "isort>=5.13.0",
+    "flake8>=7.0.0",
+    "mypy>=1.11.0",
+    "pre-commit>=4.0.0",
+]
+docs = [
+    "sphinx>=7.0.0",
+    "sphinx-rtd-theme>=2.0.0",
+    "myst-parser>=3.0.0",
+]
+test = [
+    "pytest>=8.0.0",
+    "pytest-asyncio>=0.24.0",
+    "pytest-cov>=5.0.0",
+    "httpx>=0.27.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/hivellm/vectorizer"
+Documentation = "https://github.com/hivellm/vectorizer/tree/main/docs"
+Repository = "https://github.com/hivellm/vectorizer"
+Issues = "https://github.com/hivellm/vectorizer/issues"
+
+[project.scripts]
+vectorizer-cli = "cli:main"
+
+[tool.setuptools.packages.find]
+include = ["*"]
+exclude = ["tests*", "examples*", "docs*"]
+
+[tool.setuptools.package-data]
+"*" = ["py.typed"]
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+testpaths = ["tests"]
+python_files = ["test_*.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+
+[tool.black]
+line-length = 100
+target-version = ['py38', 'py39', 'py310', 'py311', 'py312']
+
+[tool.isort]
+profile = "black"
+line_length = 100
+
+[tool.mypy]
+python_version = "3.8"
+warn_return_any = true
+warn_unused_configs = true
+disallow_untyped_defs = false
+

{vectorizer_sdk-3.0.0 → vectorizer_sdk-3.0.3}/utils/http_client.py

@@ -53,7 +53,15 @@ class HTTPClient:
         if self._session is None or self._session.closed:
             headers = {"Content-Type": "application/json"}
             if self.api_key:
-                headers["Authorization"] = f"Bearer {self.api_key}"
+                # JWT shape → `Authorization: Bearer`; anything else
+                # (raw API keys from `POST /auth/keys`) → `X-API-Key`.
+                # Server middleware won't fall back Bearer → api_key,
+                # so routing has to happen client-side.
+                parts = self.api_key.split(".")
+                if len(parts) == 3 and all(p for p in parts):
+                    headers["Authorization"] = f"Bearer {self.api_key}"
+                else:
+                    headers["X-API-Key"] = self.api_key
             
             timeout_config = aiohttp.ClientTimeout(total=self.timeout)
             self._session = aiohttp.ClientSession(

{vectorizer_sdk-3.0.0 → vectorizer_sdk-3.0.3}/vectorizer/_base.py

@@ -112,6 +112,22 @@ class RestTransport(Transport):
         await self._http.close()
 
 
+def _looks_like_jwt(token: str) -> bool:
+    """Cheap JWT shape sniff: three non-empty base64url-encoded segments
+    joined by ``.``. Raw Vectorizer API keys (from ``POST /auth/keys``)
+    are a single alphanumeric string and fail this check, so they get
+    routed to ``X-API-Key`` rather than ``Authorization: Bearer``.
+
+    The server's auth middleware treats every ``Bearer`` string as a
+    JWT and never falls back to the API-key validator, so sending a
+    raw key under ``Bearer`` silently 401s. This sniff keeps the public
+    ``api_key`` config field unchanged while routing each credential
+    down the header the server actually accepts.
+    """
+    parts = token.split(".")
+    return len(parts) == 3 and all(p for p in parts)
+
+
 @dataclass
 class AuthState:
     """Bearer-token + API-key state shared across surface clients."""
@@ -121,7 +137,9 @@ class AuthState:
     def headers(self) -> dict:
         if not self.api_key:
             return {}
-        return {"Authorization": f"Bearer {self.api_key}"}
+        if _looks_like_jwt(self.api_key):
+            return {"Authorization": f"Bearer {self.api_key}"}
+        return {"X-API-Key": self.api_key}
 
 
 @dataclass

{vectorizer_sdk-3.0.0 → vectorizer_sdk-3.0.3}/vectorizer/auth.py

@@ -22,7 +22,8 @@ class AuthClient(_ApiBase):
 
         from vectorizer import RestTransport, AuthClient
         auth = AuthClient(RestTransport("http://localhost:15002"), api_key="sk-...")
-        print(auth.headers())  # -> {"Authorization": "Bearer sk-..."}
+        print(auth.headers())  # raw API key → {"X-API-Key": "sk-..."}
+        #                      # JWT            → {"Authorization": "Bearer <jwt>"}
 
     In the :class:`vectorizer.VectorizerClient` facade this is the
     surface that owns the API key and surfaces it via :attr:`api_key`
@@ -47,3 +48,28 @@ class AuthClient(_ApiBase):
     def set_api_key(self, api_key: Optional[str]) -> None:
         """Replace the current API key — affects future request headers."""
         self._auth.api_key = api_key
+
+    async def login(self, username: str, password: str) -> str:
+        """Exchange ``(username, password)`` for a JWT via
+        ``POST /auth/login`` and return the raw ``access_token``.
+
+        The token is **not** stored on ``self`` — to use it for
+        subsequent requests, call :meth:`set_api_key` with the token
+        (``AuthState.headers`` sniffs the JWT shape and routes it onto
+        ``Authorization: Bearer …`` automatically).
+
+        When the server runs with ``auth.enabled: false`` this
+        endpoint returns 404 — dev servers without auth don't need
+        to call :meth:`login` at all.
+        """
+        data = await self._transport.post(
+            "/auth/login",
+            {"username": username, "password": password},
+        )
+        token = data.get("access_token") if isinstance(data, dict) else None
+        if not isinstance(token, str) or not token:
+            raise ValueError(
+                "login response missing `access_token`; server payload: "
+                f"{data!r}"
+            )
+        return token

{vectorizer_sdk-3.0.0 → vectorizer_sdk-3.0.3}/vectorizer/client.py

@@ -274,7 +274,16 @@ class VectorizerClient:
             if self._session is None or self._session.closed:
                 headers = {}
                 if self.api_key:
-                    headers["Authorization"] = f"Bearer {self.api_key}"
+                    # Route JWTs to `Authorization: Bearer` and raw API
+                    # keys to `X-API-Key`. Server middleware treats
+                    # every Bearer string as a JWT and won't fall back
+                    # to the API-key validator — sending a raw key as
+                    # Bearer silently 401s on every gated route.
+                    from ._base import _looks_like_jwt
+                    if _looks_like_jwt(self.api_key):
+                        headers["Authorization"] = f"Bearer {self.api_key}"
+                    else:
+                        headers["X-API-Key"] = self.api_key
 
                 timeout = aiohttp.ClientTimeout(total=self.timeout)
                 self._session = aiohttp.ClientSession(

{vectorizer_sdk-3.0.0 → vectorizer_sdk-3.0.3}/vectorizer/vectors.py

@@ -112,6 +112,15 @@ class VectorsClient(_ApiBase):
         """
         Get a specific vector by ID.
 
+        .. warning::
+           **Server caveat (observed on ``hivehub/vectorizer:3.0.x``):**
+           this endpoint currently returns HTTP 200 with a synthetic
+           uniform-vector payload (``[0.1, 0.1, ...]``) even for ids
+           that don't exist. Callers that need real miss detection
+           should probe via :meth:`list_vectors` or search and not
+           trust a successful response as proof of existence until
+           the server fix ships.
+
         Args:
             collection: Collection name
             vector_id: Vector ID
@@ -125,6 +134,44 @@ class VectorsClient(_ApiBase):
             ServerError: If service returns error
         """
         return await self._transport.get(f"/collections/{collection}/vectors/{vector_id}")
+
+    async def insert_text_batch(
+        self,
+        collection: str,
+        texts: List[Dict[str, Any]],
+    ) -> Dict[str, Any]:
+        """Insert a batch of **texts** into a collection. The server
+        embeds each entry with the collection's configured provider
+        (BM25 default, FastEmbed ONNX when selected in ``config.yml``).
+
+        Wire contract: ``POST /insert_texts`` with
+        ``{"collection": ..., "texts": [...]}`` payload. The collection
+        is a top-level JSON field, **not** a path segment.
+
+        Per-entry ``id``: the server **reassigns** every inserted
+        vector a server-generated UUID. The original client id
+        round-trips on the response as ``client_id``. Callers that
+        need idempotency by client id should key off the returned
+        ``results[].client_id``, not the server-assigned UUID.
+
+        Distinct from :meth:`insert_texts` on this class, which takes
+        :class:`Vector` objects with pre-computed embeddings and hits
+        the raw-vector write path.
+
+        Args:
+            collection: Collection name.
+            texts: Entries of shape
+                ``{"id": "...", "text": "...", "metadata": {...}}``.
+
+        Returns:
+            Raw ``/insert_texts`` response dict with fields
+            ``collection``, ``count``, ``inserted``, ``failed``,
+            ``results``.
+        """
+        if not texts:
+            raise ValidationError("texts list cannot be empty")
+        payload = {"collection": collection, "texts": texts}
+        return await self._transport.post("/insert_texts", data=payload)
     async def delete_vectors(self, collection: str, vector_ids: List[str]) -> bool:
         """
         Delete vectors from a collection.

{vectorizer_sdk-3.0.0 → vectorizer_sdk-3.0.3/vectorizer_sdk.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: vectorizer_sdk
-Version: 3.0.0
+Version: 3.0.3
 Summary: Python SDK for Vectorizer - Semantic search, vector operations, and the VectorizerRPC binary transport (default in v3.x)
 Author-email: HiveLLM Team <team@hivellm.org>
 License: Apache-2.0