diff --git a/docs/index.html b/docs/index.html new file mode 100644 index 0000000..42cf4f7 --- /dev/null +++ b/docs/index.html @@ -0,0 +1,531 @@ + + +
+ + +Index your entire OpenClaw workspace โ chat history, code, documentation โ and search by meaning, not keywords. Fully offline, zero dependencies, complete privacy.
+ +๐ Found 3 relevant items:
+๐ Past Conversation (voipms-sms)
+Use voipms_sms_client.py with API endpoint...
+API: https://voip.ms/api/v1/rest.php
+โ Indexed 2,533 documents from your workspace
+Everything you need to build and maintain your knowledge base
+Find context by meaning, not just keywords. ChromaDB with all-MiniLM-L6-v2 embeddings automatically understands the intent behind your queries.
+Index chat sessions, Python/JavaScript code, Markdown docs, skill documentation โ everything in your OpenClaw workspace becomes searchable.
+No API keys, no external services, no cloud databases. All embeddings and storage live on your machine. Your data never leaves.
+The AI automatically retrieves relevant context from your knowledge base when responding. It "remembers" your past work transparently.
+Search by document type โ sessions, workspace, skills, memory. Find exactly what you're looking for with precision.
+Indexing at ~1,000 docs/minute, search in under 100ms. The embedding model (79MB) caches locally after first run.
+Compare with web-search RAG tools
+Different use cases for different problems
+Need current information, multi-engine web searches, or gathering context from the internet? That's what web-search RAG tools do best.
+Need to find past solutions, code patterns, decisions, or conversations? That's our specialty โ we remember everything you've done.
+Use web-search RAG for research, then save the important findings to your knowledge base. OpenClaw RAG preserves what matters forever.
+