AI Tools

Bewerter für RAG-Chunk-Qualität

Bewertet Kandidaten-Schemata für die RAG-Chunk-Aufteilung eines Dokuments nach vier Metriken — Kohärenz (saubere Satz-/Absatzgrenzen), Abdeckung (thematischer Fokus / Schlüsselwort-Konzentration), Gesundheit der Kontextüberlappung und Größenkonsistenz — vergleicht bis zu drei Schemata und empfiehlt das beste. Reine Offline-Heuristiken, keine Modellaufrufe.

html· HTML-ErgebnisWerkzeug öffnen

Schnellstart

Rufen Sie dieses Werkzeug aus Ihrem Code in drei Sprachen auf.

cURL

curl -X POST 'https://api.elysiatools.com/de/api/tools/ai-rag-chunk-quality-scorer' \
  -H 'Content-Type: application/json' \
  -d '{"document":"Retrieval-augmented generation combines a retriever and a language model. The retriever finds relevant passages in a knowledge base. Chunking strategy strongly affects retrieval quality. Smaller chunks are precise but lose context. Larger chunks carry context but dilute relevance. Overlap between chunks preserves context across boundaries. Evaluate several schemes before indexing.","unit":"tokens","method":"sentence","sizeA":256,"overlapA":32,"sizeB":512,"overlapB":64,"sizeC":1024,"overlapC":128,"renderMode":"comparison","precision":1}'

Werkzeuge durchsuchen

AI Tools

Bewerter für RAG-Chunk-Qualität

html· HTML-ErgebnisWerkzeug öffnen

Schnellstart

Rufen Sie dieses Werkzeug aus Ihrem Code in drei Sprachen auf.

cURL

curl -X POST 'https://api.elysiatools.com/de/api/tools/ai-rag-chunk-quality-scorer' \
  -H 'Content-Type: application/json' \
  -d '{"document":"Retrieval-augmented generation combines a retriever and a language model. The retriever finds relevant passages in a knowledge base. Chunking strategy strongly affects retrieval quality. Smaller chunks are precise but lose context. Larger chunks carry context but dilute relevance. Overlap between chunks preserves context across boundaries. Evaluate several schemes before indexing.","unit":"tokens","method":"sentence","sizeA":256,"overlapA":32,"sizeB":512,"overlapB":64,"sizeC":1024,"overlapC":128,"renderMode":"comparison","precision":1}'

Name	Typ	Erforderlich	Beschreibung
document	textarea	Ja	—
unit	select	Nein	—
method	select	Nein	—
sizeA	number	Ja	—
overlapA	number	Nein	—
sizeB	number	Ja	—
overlapB	number	Nein	—
sizeC	number	Ja	—
overlapC	number	Nein	—
renderMode	select	Nein	—
precision	number	Ja	—

{ "mcpServers": { "elysiatools-ai-rag-chunk-quality-scorer": { "name": "ai-rag-chunk-quality-scorer", "description": "Bewertet Kandidaten-Schemata für die RAG-Chunk-Aufteilung eines Dokuments nach vier Metriken — Kohärenz (saubere Satz-/Absatzgrenzen), Abdeckung (thematischer Fokus / Schlüsselwort-Konzentration), Gesundheit der Kontextüberlappung und Größenkonsistenz — vergleicht bis zu drei Schemata und empfiehlt das beste. Reine Offline-Heuristiken, keine Modellaufrufe.", "baseUrl": "https://api.elysiatools.com/mcp/sse?toolId=ai-rag-chunk-quality-scorer", "command": "", "args": [], "env": {}, "isActive": true, "type": "sse" } } }

{ "jsonrpc": "2.0", "id": 2, "method": "tools/call", "params": { "name": "ai-rag-chunk-quality-scorer", "arguments": { "document": "Retrieval-augmented generation combines a retriever and a language model. The retriever finds relevant passages in a knowledge base. Chunking strategy strongly affects retrieval quality. Smaller chunks are precise but lose context. Larger chunks carry context but dilute relevance. Overlap between chunks preserves context across boundaries. Evaluate several schemes before indexing.", "unit": "tokens", "method": "sentence", "sizeA": 256, "overlapA": 32, "sizeB": 512, "overlapB": 64, "sizeC": 1024, "overlapC": 128, "renderMode": "comparison", "precision": 1 } } }

Bewerter für RAG-Chunk-Qualität

Schnellstart

Bewerter für RAG-Chunk-Qualität

Schnellstart

API-Referenz

Endpunkt

Parameter

Antwortformat

MCP-Integration

Serverkonfiguration

Verfügbare Werkzeuge auflisten

Dieses Werkzeug aufrufen