<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[Iceberg DB]]></title><description><![CDATA[Iceberg DB]]></description><link>https://icebergdb.hashnode.dev</link><image><url>https://cdn.hashnode.com/uploads/logos/6ad8226059e12396314d97bf/3d07dea9-1597-444d-8542-2cf23279dabd.png</url><title>Iceberg DB</title><link>https://icebergdb.hashnode.dev</link></image><generator>RSS for Node</generator><lastBuildDate>Sun, 25 Oct 2026 10:27:30 GMT</lastBuildDate><atom:link href="https://icebergdb.hashnode.dev/rss.xml" rel="self" type="application/rss+xml"/><language><![CDATA[en]]></language><ttl>60</ttl><item><title><![CDATA[Introducing Iceberg DB: India's Serverless Vector Database & AI Agent Memory Engine (<20ms Latency)]]></title><description><![CDATA[While building RAG pipelines and autonomous AI agents in India, I kept hitting the same three walls with US-hosted vector databases: 200ms+ Network…]]></description><link>https://icebergdb.hashnode.dev/introducing-iceberg-db-india-s-serverless-vector-database-ai-agent-memory-engine-20ms-latency</link><guid isPermaLink="true">https://icebergdb.hashnode.dev/introducing-iceberg-db-india-s-serverless-vector-database-ai-agent-memory-engine-20ms-latency</guid><category><![CDATA[AI]]></category><category><![CDATA[Python]]></category><category><![CDATA[database]]></category><category><![CDATA[vector database]]></category><dc:creator><![CDATA[iceberg]]></dc:creator><pubDate>Wed, 21 Oct 2026 03:23:19 GMT</pubDate><content:encoded><![CDATA[<p>While building RAG pipelines and autonomous AI agents in India, I kept hitting the same three walls with US-hosted vector databases:</p>
<ol>
<li><p><strong>200ms+ Network Latency:</strong> Every vector search from India to <code>us-east-1</code> adds ~200ms of round-trip latency before the LLM even starts generating.</p>
</li>
<li><p><strong>Paused Free Tiers:</strong> Free tier pods pause after a few days of inactivity, breaking live projects and demos.</p>
</li>
<li><p><strong>Boilerplate Overload:</strong> Raw vector databases only store float arrays—you still have to wire up document chunking, external embedding APIs, BM25 keyword + dense vector Reciprocal Rank Fusion (RRF), and TTL jobs for agent session memory.</p>
</li>
</ol>
<p>Today, I'm excited to launch <a href="https://icebergdb.in"><strong>Iceberg DB</strong></a> — a serverless vector database and cognitive memory platform hosted in Mumbai (<code>ap-south-1</code>).</p>
<hr />
<h3>⚡ What Iceberg DB Gives You Out of the Box</h3>
<ul>
<li><p><strong>&lt;20ms Query Latency in India:</strong> Hosted in Mumbai with 100% Indian data residency (DPDP Act 2023 compliant).</p>
</li>
<li><p><strong>Built-in Hybrid Search (RRF):</strong> Combines dense semantic vectors + sparse BM25 keyword search in a single API call (<code>alpha</code> slider from <code>0.0</code> to <code>1.0</code>).</p>
</li>
<li><p><strong>Native 4-Tier AI Agent Memory:</strong> Give your AI agents persistent memory across sessions (<code>short_term</code> with 1hr TTL, <code>episodic</code> with 30-day TTL, <code>long_term</code>, and <code>semantic</code>).</p>
</li>
<li><p><strong>Built-in Neural Embeddings:</strong> Send raw text or upload PDFs directly—no separate OpenAI or Cohere embedding API key required.</p>
</li>
<li><p><strong>Forever Free Tier (Never Pauses):</strong> 100,000 vectors free forever, zero cold-start pausing, no credit card required.</p>
</li>
</ul>
<hr />
<h3>🐍 5-Line Python Quickstart (<code>pip install iceberg-sdk</code>)</h3>
<pre><code class="language-python">from iceberg import Client

client = Client(api_key="ib_your_key")

# 1. Create a collection &amp; index raw text (embeddings generated automatically)
client.create_collection("my_docs")
client.index_text("my_docs", "Iceberg DB is hosted in Mumbai with sub-20ms latency.")

# 2. Hybrid Search (Dense + BM25)
results = client.search("my_docs", "where is Iceberg hosted?", search_type="hybrid")
for r in results:
    print(f"{r.score:.2f} - {r.text}")

# 3. Persistent Agent Memory
client.memory.remember("agent_01", "User prefers concise Python code", memory_type="long_term")
memories = client.memory.recall("agent_01", "how should I format answers?")
</code></pre>
<h3>🔗 Try It Live</h3>
<ul>
<li><p><strong>Website &amp; Interactive Search Demo:</strong> <a href="https://icebergdb.in">https://icebergdb.in</a></p>
</li>
<li><p><strong>Cloud Console (Get Free API Key in 30s):</strong> <a href="https://dashboard.icebergdb.in/signup">https://dashboard.icebergdb.in/signup</a></p>
</li>
<li><p><strong>Documentation:</strong> <a href="https://icebergdb.in/docs">https://icebergdb.in/docs</a></p>
</li>
<li><p><strong>Interactive API Playground:</strong> <a href="https://api.icebergdb.in/docs">https://api.icebergdb.in/docs</a></p>
</li>
</ul>
<p>I'd love for you to test it out and share your feedback!</p>
]]></content:encoded></item></channel></rss>