icebergdb 0.1.0__tar.gz

icebergdb-0.1.0/PKG-INFO

@@ -0,0 +1,111 @@
+Metadata-Version: 2.4
+Name: icebergdb
+Version: 0.1.0
+Summary: Iceberg — High-performance serverless vector database for AI agents and RAG applications
+Home-page: https://icebergdb.in
+Author: Iceberg Data Technologies
+Author-email: Iceberg Data Technologies <hello@icebergdb.in>
+License: MIT
+Project-URL: Homepage, https://icebergdb.in
+Project-URL: Documentation, https://icebergdb.in/docs
+Project-URL: Repository, https://github.com/icebergdb/iceberg
+Project-URL: Issues, https://github.com/icebergdb/iceberg/issues
+Keywords: vector database,vector search,rag,ai agents,embeddings,semantic search
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Database
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: httpx>=0.27.0
+Dynamic: author
+Dynamic: home-page
+Dynamic: requires-python
+
+<p align="center">
+  <h1 align="center">⚡ Iceberg Database</h1>
+  <p align="center"><strong>High-performance serverless vector database built for AI agents and real-time RAG.</strong></p>
+</p>
+
+<p align="center">
+  <a href="https://icebergdb.in"><img src="https://img.shields.io/badge/Status-Active-22c55e?style=flat-square" alt="Status"></a>
+  <a href="https://pypi.org/project/icebergdb/"><img src="https://img.shields.io/badge/pypi-v0.1.0-38bdf8?style=flat-square" alt="PyPI"></a>
+  <a href="https://python.org"><img src="https://img.shields.io/badge/python-3.9+-blue?style=flat-square" alt="Python"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-purple?style=flat-square" alt="License"></a>
+</p>
+
+---
+
+## 🚀 Quick Install
+
+```bash
+pip install icebergdb
+```
+
+---
+
+## ⚡ 30-Second Quickstart
+
+```python
+import iceberg
+
+# 1. Connect to Iceberg (reads ICEBERG_API_KEY from environment by default)
+db = iceberg.connect(api_key="your_api_key")
+
+# 2. Create an isolated vector collection
+db.create_collection("ai_agent_memory", description="Real-time context memory")
+
+# 3. Index text documents or chunks (supports English, Hindi, and multilingual text)
+db.index_text("ai_agent_memory", "Iceberg delivers sub-5ms vector queries with zero cold starts.")
+db.index_text("ai_agent_memory", "Autonomous AI agents require persistent, low-latency recall memory.")
+
+# 4. Perform hybrid semantic search
+results = db.search("ai_agent_memory", query="low-latency agent recall", top_k=3)
+
+for match in results:
+    print(f"[{match.score:.3f}] {match.text}")
+```
+
+---
+
+## 📁 Uploading Documents Directly (PDF, TXT, Markdown)
+
+```python
+# Upload and auto-chunk entire documents in one line
+db.upload("ai_agent_memory", "product_spec.pdf")
+```
+
+---
+
+## 🔍 Filtered & Scoped Search
+
+```python
+results = db.search(
+    "ai_agent_memory",
+    query="vector benchmarks",
+    top_k=5,
+    score_threshold=0.4,
+    filters={"source": "product_spec.pdf"}
+)
+```
+
+---
+
+## 🌐 Cloud & Self-Hosted Endpoints
+
+To connect to your local dev engine or dedicated cluster:
+
+```python
+db = iceberg.connect(
+    api_key="iceberg_secret_key",
+    base_url="http://localhost:8000"  # or https://api.icebergdb.in
+)
+```
+
+---
+
+## 🛡️ License
+
+MIT License © 2026 Iceberg Data Technologies.

icebergdb-0.1.0/README.md

@@ -0,0 +1,85 @@
+<p align="center">
+  <h1 align="center">⚡ Iceberg Database</h1>
+  <p align="center"><strong>High-performance serverless vector database built for AI agents and real-time RAG.</strong></p>
+</p>
+
+<p align="center">
+  <a href="https://icebergdb.in"><img src="https://img.shields.io/badge/Status-Active-22c55e?style=flat-square" alt="Status"></a>
+  <a href="https://pypi.org/project/icebergdb/"><img src="https://img.shields.io/badge/pypi-v0.1.0-38bdf8?style=flat-square" alt="PyPI"></a>
+  <a href="https://python.org"><img src="https://img.shields.io/badge/python-3.9+-blue?style=flat-square" alt="Python"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-purple?style=flat-square" alt="License"></a>
+</p>
+
+---
+
+## 🚀 Quick Install
+
+```bash
+pip install icebergdb
+```
+
+---
+
+## ⚡ 30-Second Quickstart
+
+```python
+import iceberg
+
+# 1. Connect to Iceberg (reads ICEBERG_API_KEY from environment by default)
+db = iceberg.connect(api_key="your_api_key")
+
+# 2. Create an isolated vector collection
+db.create_collection("ai_agent_memory", description="Real-time context memory")
+
+# 3. Index text documents or chunks (supports English, Hindi, and multilingual text)
+db.index_text("ai_agent_memory", "Iceberg delivers sub-5ms vector queries with zero cold starts.")
+db.index_text("ai_agent_memory", "Autonomous AI agents require persistent, low-latency recall memory.")
+
+# 4. Perform hybrid semantic search
+results = db.search("ai_agent_memory", query="low-latency agent recall", top_k=3)
+
+for match in results:
+    print(f"[{match.score:.3f}] {match.text}")
+```
+
+---
+
+## 📁 Uploading Documents Directly (PDF, TXT, Markdown)
+
+```python
+# Upload and auto-chunk entire documents in one line
+db.upload("ai_agent_memory", "product_spec.pdf")
+```
+
+---
+
+## 🔍 Filtered & Scoped Search
+
+```python
+results = db.search(
+    "ai_agent_memory",
+    query="vector benchmarks",
+    top_k=5,
+    score_threshold=0.4,
+    filters={"source": "product_spec.pdf"}
+)
+```
+
+---
+
+## 🌐 Cloud & Self-Hosted Endpoints
+
+To connect to your local dev engine or dedicated cluster:
+
+```python
+db = iceberg.connect(
+    api_key="iceberg_secret_key",
+    base_url="http://localhost:8000"  # or https://api.icebergdb.in
+)
+```
+
+---
+
+## 🛡️ License
+
+MIT License © 2026 Iceberg Data Technologies.

icebergdb-0.1.0/iceberg/__init__.py

@@ -0,0 +1,20 @@
+from .client import Client, SearchResult, IcebergError
+from typing import Optional
+
+__version__ = "0.1.0"
+__all__ = ["Client", "SearchResult", "IcebergError", "connect"]
+
+
+def connect(
+    api_key: Optional[str] = None,
+    base_url: Optional[str] = None,
+    timeout: float = 30.0,
+) -> Client:
+    """
+    Connect to Iceberg Vector Database.
+    
+    Example:
+        import iceberg
+        db = iceberg.connect(api_key="your_key")
+    """
+    return Client(api_key=api_key, base_url=base_url, timeout=timeout)

icebergdb-0.1.0/iceberg/client.py

@@ -0,0 +1,166 @@
+import os
+import httpx
+from typing import Optional, List, Dict, Any
+
+
+class IcebergError(Exception):
+    pass
+
+
+class SearchResult:
+    def __init__(self, data: dict):
+        self.text: str = data.get("text", "")
+        self.score: float = data.get("score", 0.0)
+        self.metadata: dict = data.get("metadata", {})
+
+    def __repr__(self):
+        return f"SearchResult(score={self.score:.3f}, text={self.text[:60]!r})"
+
+
+class Client:
+    """
+    Iceberg API Client
+
+    Usage:
+        import iceberg
+
+        client = iceberg.connect(api_key="your_api_key")
+
+        # Create a collection
+        client.create_collection("my_docs")
+
+        # Index text
+        client.index_text("my_docs", "Your document text here")
+
+        # Upload a PDF
+        client.upload("my_docs", "document.pdf")
+
+        # Search
+        results = client.search("my_docs", "your query")
+        for r in results:
+            print(r.score, r.text)
+    """
+
+    def __init__(
+        self,
+        api_key: Optional[str] = None,
+        base_url: Optional[str] = None,
+        timeout: float = 30.0,
+    ):
+        self.api_key = api_key or os.environ.get("ICEBERG_API_KEY", "")
+        resolved_url = base_url or os.environ.get("ICEBERG_API_URL", "https://api.icebergdb.in")
+        self.base_url = resolved_url.rstrip("/")
+        
+        headers = {}
+        if self.api_key:
+            headers["X-API-Key"] = self.api_key
+
+        self._client = httpx.Client(
+            headers=headers,
+            timeout=timeout,
+        )
+
+    def _get(self, path: str, **kwargs):
+        r = self._client.get(f"{self.base_url}{path}", **kwargs)
+        self._raise(r)
+        return r.json()
+
+    def _post(self, path: str, **kwargs):
+        r = self._client.post(f"{self.base_url}{path}", **kwargs)
+        self._raise(r)
+        return r.json()
+
+    def _delete(self, path: str):
+        r = self._client.delete(f"{self.base_url}{path}")
+        self._raise(r)
+        return r.json()
+
+    def _raise(self, r: httpx.Response):
+        if r.status_code >= 400:
+            try:
+                detail = r.json().get("detail", r.text)
+            except Exception:
+                detail = r.text
+            raise IcebergError(f"HTTP {r.status_code}: {detail}")
+
+    # ── Collections ──────────────────────────────────────────────────────────
+
+    def create_collection(self, name: str, description: str = "") -> dict:
+        """Create a new vector collection."""
+        return self._post("/collections", json={"name": name, "description": description})
+
+    def list_collections(self) -> list[str]:
+        """List all collection names."""
+        return self._get("/collections").get("collections", [])
+
+    def delete_collection(self, name: str) -> dict:
+        """Delete a collection and all its vectors."""
+        return self._delete(f"/collections/{name}")
+
+    def collection_info(self, name: str) -> dict:
+        """Get info about a collection (vector count, status)."""
+        return self._get(f"/collections/{name}")
+
+    # ── Indexing ──────────────────────────────────────────────────────────────
+
+    def index_text(self, collection: str, text: str, source: str = "sdk") -> dict:
+        """
+        Index plain text into a collection.
+        The text is automatically chunked and embedded.
+        """
+        return self._post("/documents/text", data={
+            "collection": collection,
+            "text": text,
+            "source": source,
+        })
+
+    def upload(self, collection: str, file_path: str) -> dict:
+        """Upload and index a file (PDF, TXT, MD)."""
+        with open(file_path, "rb") as f:
+            filename = file_path.split("/")[-1].split("\\")[-1]
+            r = self._client.post(
+                f"{self.base_url}/documents/upload",
+                data={"collection": collection},
+                files={"file": (filename, f)},
+            )
+        self._raise(r)
+        return r.json()
+
+    # ── Search ────────────────────────────────────────────────────────────────
+
+    def search(
+        self,
+        collection: str,
+        query: str,
+        top_k: int = 5,
+        score_threshold: float = 0.3,
+        filters: Optional[dict] = None,
+    ) -> list[SearchResult]:
+        """Semantic search in a collection."""
+        payload = {
+            "collection": collection,
+            "query": query,
+            "top_k": top_k,
+            "score_threshold": score_threshold,
+        }
+        if filters:
+            payload["filters"] = filters
+
+        data = self._post("/search", json=payload)
+        return [SearchResult(r) for r in data.get("results", [])]
+
+    # ── Usage ─────────────────────────────────────────────────────────────────
+
+    def usage_stats(self) -> dict:
+        """Get usage statistics for your account."""
+        return self._get("/usage/stats")
+
+    def close(self):
+        """Close the HTTP client."""
+        self._client.close()
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, *args):
+        self.close()

icebergdb-0.1.0/icebergdb.egg-info/PKG-INFO

@@ -0,0 +1,111 @@
+Metadata-Version: 2.4
+Name: icebergdb
+Version: 0.1.0
+Summary: Iceberg — High-performance serverless vector database for AI agents and RAG applications
+Home-page: https://icebergdb.in
+Author: Iceberg Data Technologies
+Author-email: Iceberg Data Technologies <hello@icebergdb.in>
+License: MIT
+Project-URL: Homepage, https://icebergdb.in
+Project-URL: Documentation, https://icebergdb.in/docs
+Project-URL: Repository, https://github.com/icebergdb/iceberg
+Project-URL: Issues, https://github.com/icebergdb/iceberg/issues
+Keywords: vector database,vector search,rag,ai agents,embeddings,semantic search
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Database
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: httpx>=0.27.0
+Dynamic: author
+Dynamic: home-page
+Dynamic: requires-python
+
+<p align="center">
+  <h1 align="center">⚡ Iceberg Database</h1>
+  <p align="center"><strong>High-performance serverless vector database built for AI agents and real-time RAG.</strong></p>
+</p>
+
+<p align="center">
+  <a href="https://icebergdb.in"><img src="https://img.shields.io/badge/Status-Active-22c55e?style=flat-square" alt="Status"></a>
+  <a href="https://pypi.org/project/icebergdb/"><img src="https://img.shields.io/badge/pypi-v0.1.0-38bdf8?style=flat-square" alt="PyPI"></a>
+  <a href="https://python.org"><img src="https://img.shields.io/badge/python-3.9+-blue?style=flat-square" alt="Python"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-purple?style=flat-square" alt="License"></a>
+</p>
+
+---
+
+## 🚀 Quick Install
+
+```bash
+pip install icebergdb
+```
+
+---
+
+## ⚡ 30-Second Quickstart
+
+```python
+import iceberg
+
+# 1. Connect to Iceberg (reads ICEBERG_API_KEY from environment by default)
+db = iceberg.connect(api_key="your_api_key")
+
+# 2. Create an isolated vector collection
+db.create_collection("ai_agent_memory", description="Real-time context memory")
+
+# 3. Index text documents or chunks (supports English, Hindi, and multilingual text)
+db.index_text("ai_agent_memory", "Iceberg delivers sub-5ms vector queries with zero cold starts.")
+db.index_text("ai_agent_memory", "Autonomous AI agents require persistent, low-latency recall memory.")
+
+# 4. Perform hybrid semantic search
+results = db.search("ai_agent_memory", query="low-latency agent recall", top_k=3)
+
+for match in results:
+    print(f"[{match.score:.3f}] {match.text}")
+```
+
+---
+
+## 📁 Uploading Documents Directly (PDF, TXT, Markdown)
+
+```python
+# Upload and auto-chunk entire documents in one line
+db.upload("ai_agent_memory", "product_spec.pdf")
+```
+
+---
+
+## 🔍 Filtered & Scoped Search
+
+```python
+results = db.search(
+    "ai_agent_memory",
+    query="vector benchmarks",
+    top_k=5,
+    score_threshold=0.4,
+    filters={"source": "product_spec.pdf"}
+)
+```
+
+---
+
+## 🌐 Cloud & Self-Hosted Endpoints
+
+To connect to your local dev engine or dedicated cluster:
+
+```python
+db = iceberg.connect(
+    api_key="iceberg_secret_key",
+    base_url="http://localhost:8000"  # or https://api.icebergdb.in
+)
+```
+
+---
+
+## 🛡️ License
+
+MIT License © 2026 Iceberg Data Technologies.

icebergdb-0.1.0/icebergdb.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+README.md
+pyproject.toml
+setup.py
+iceberg/__init__.py
+iceberg/client.py
+icebergdb.egg-info/PKG-INFO
+icebergdb.egg-info/SOURCES.txt
+icebergdb.egg-info/dependency_links.txt
+icebergdb.egg-info/requires.txt
+icebergdb.egg-info/top_level.txt

icebergdb-0.1.0/icebergdb.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

icebergdb-0.1.0/icebergdb.egg-info/requires.txt

@@ -0,0 +1 @@
+httpx>=0.27.0

icebergdb-0.1.0/icebergdb.egg-info/top_level.txt

@@ -0,0 +1 @@
+iceberg

icebergdb-0.1.0/pyproject.toml

@@ -0,0 +1,32 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "icebergdb"
+version = "0.1.0"
+description = "Iceberg — High-performance serverless vector database for AI agents and RAG applications"
+readme = "README.md"
+requires-python = ">=3.9"
+license = { text = "MIT" }
+authors = [
+    { name = "Iceberg Data Technologies", email = "hello@icebergdb.in" }
+]
+keywords = ["vector database", "vector search", "rag", "ai agents", "embeddings", "semantic search"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Topic :: Database",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+]
+dependencies = [
+    "httpx>=0.27.0",
+]
+
+[project.urls]
+Homepage = "https://icebergdb.in"
+Documentation = "https://icebergdb.in/docs"
+Repository = "https://github.com/icebergdb/iceberg"
+Issues = "https://github.com/icebergdb/iceberg/issues"

icebergdb-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

icebergdb-0.1.0/setup.py

@@ -0,0 +1,61 @@
+import os
+from setuptools import setup, find_packages
+
+here = os.path.abspath(os.path.dirname(__file__))
+readme_path = os.path.join(here, "README.md")
+long_description = ""
+if os.path.exists(readme_path):
+    with open(readme_path, encoding="utf-8") as f:
+        long_description = f.read()
+
+setup(
+    name="icebergdb",
+    version="0.1.0",
+    description="Iceberg — High-performance serverless vector database for AI agents and RAG applications",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    author="Iceberg Data Technologies",
+    author_email="hello@icebergdb.in",
+    url="https://icebergdb.in",
+    project_urls={
+        "Documentation": "https://icebergdb.in/docs",
+        "Source": "https://github.com/icebergdb/iceberg",
+        "Bug Tracker": "https://github.com/icebergdb/iceberg/issues",
+    },
+    license="MIT",
+    packages=find_packages(),
+    python_requires=">=3.9",
+    install_requires=[
+        "httpx>=0.27.0",
+    ],
+    extras_require={
+        "dev": [
+            "pytest>=8.0.0",
+            "build>=1.0.0",
+            "twine>=5.0.0",
+        ],
+    },
+    keywords=[
+        "vector database",
+        "vector search",
+        "rag",
+        "ai agents",
+        "embeddings",
+        "semantic search",
+        "llm",
+    ],
+    classifiers=[
+        "Development Status :: 4 - Beta",
+        "Intended Audience :: Developers",
+        "Intended Audience :: Science/Research",
+        "Topic :: Database",
+        "Topic :: Scientific/Engineering :: Artificial Intelligence",
+        "License :: OSI Approved :: MIT License",
+        "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
+        "Operating System :: OS Independent",
+    ],
+)