Discovered via unknown and last synced 3mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
Extension
JSON
int
Results returned when no limit specified
string
`.md`
`.csv`
`.xml`
H
bool
0
Root element and namespace extraction
JSX<br/>TS
string
Default
`.py`
add
NOFILTER end subgraph HYBRID["Hybrid Search"] direction LR SEMANTIC["Semantic Search<br/>(ChromaDB embeddings)<br/>Conceptual similarity"] BM25["BM25 Search<br/>(expanded query)<br/>Exact term matching"] end subgraph FUSION["Result Fusion + Reranking"] RRF["Reciprocal Rank Fusion<br/>score = alpha * 1/(k+rank_sem)<br/>+ (1-alpha) * 1/(k+rank_bm25)"] RERANK["Cross-Encoder Reranker<br/>Re-scores top 3x candidates<br/>query+doc pair scoring"] SORT["Sort by Reranker Score<br/>Normalize to 0-1"] RRF --> RERANK --> SORT end CATEGORY --> HYBRID NOFILTER --> HYBRID SEMANTIC --> RRF BM25 --> RRF SORT --> RESULTS["Results<br/>search_method: hybrid
string
Expansions
TXT
`.js`
PPTX
string
bool
string (JSON)
Max characters per chunk
Hard cap even if client requests more
Notes
bool
Enable cross-encoder reranking
`.docx`
`.pptx`
`.ts`
stats
string
200+
Vector dimensions (must match model)
General queries
XML
evaluate"] end subgraph SEARCH["HYBRID SEARCH ENGINE"] direction LR ROUTER["Keyword Router<br/>(word boundaries)"] SEMANTIC["Semantic Search<br/>(ChromaDB)"] BM25["BM25 Keyword<br/>(rank-bm25 + expansion)"] RRF["Reciprocal Rank<br/>Fusion (RRF)"] RERANK["Cross-Encoder<br/>Reranker"] ROUTER --> SEMANTIC ROUTER --> BM25 SEMANTIC --> RRF BM25 --> RRF RRF --> RERANK end subgraph STORAGE["STORAGE LAYER"] direction LR CHROMA[("ChromaDB<br/>Vector Database")] COLLECTIONS["Collections<br/>security
Type
100+
Enable CUDA GPU acceleration. Requires `pip install knowledge-rag[gpu]`
Conceptual queries, related topics
`.xlsx`
Description
MQ4"] CHUNKER["Chunking<br/>MD: section-aware<br/>Other: 1000 chars + 200 overlap"] PARSERS --> CHUNKER end CLAUDE["Claude Code"] --> MCP MCP --> SEARCH SEARCH --> STORAGE STORAGE --> EMBED INGEST --> EMBED EMBED --> STORAGE ``` ### Query Processing Flow ```mermaid flowchart TB QUERY["User Query<br/>'mimikatz credential dump'"] --> EXPAND subgraph EXPANSION["Query Expansion"] EXPAND["Synonym Expansion<br/>mimikatz -> mimikatz, sekurlsa, logonpasswords"] end EXPAND --> ROUTER subgraph ROUTING["Keyword Routing"] ROUTER["Keyword Router"] MATCH{"Word Boundary<br/>Match?"} CATEGORY["Filter: redteam"] NOFILTER["No Filter"] ROUTER --> MATCH MATCH -->
Behavior
string
File
Characters shared between consecutive chunks
ChromaDB collection — change for separate KBs
Fetch N*multiplier candidates for reranking