Smart RAG API
# Wauldo — AI Reliability Layer **Your AI is already wrong in production. Guard catches it.** Wauldo Guard verifies every LLM response against your source documents. Wrong answers get blocked before they reach your users. 2 lines of code. Demo: [https://wauldo.com/demo](https://wauldo.com/demo) Docs: [https://wauldo.com/docs](https://wauldo.com/docs) Postman:…
3 subscribers
8.5/10 popularity
2793 ms avg latency
93% success rate
90 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
Smart RAG API endpoints
| Method | Endpoint | Description |
|---|---|---|
| Documents | ||
| GET |
listDocuments /v1/documents |
List all indexed documents with metadata, chunk count, token count, and content preview. |
| POST |
uploadFile /v1/upload-file |
Upload a file via multipart form. Supported: .pdf, .docx, .txt, .md, .json, .yaml, .html, .csv, .rs, .py, .js, .ts, .png, .jpg, .gif, .webp. Max 10 MB. PDF and DOCX text is… |
| DELETE |
deleteDocument /v1/documents/{document_id} |
Delete a specific document and all its chunks. Irreversible. |
| POST |
uploadDocument /v1/upload |
Upload text content for RAG indexing. Automatically chunked for optimal retrieval. Max 10 MB, max 5000 chunks. |
| Query | ||
| POST |
queryDocuments /v1/query |
Ask a question and get an AI-generated answer with source citations and full audit trail. Uses hybrid retrieval (BM25 + semantic) with smart cost routing. |
| Chat | ||
| POST |
chatCompletions /v1/chat/completions |
OpenAI-compatible chat completions endpoint. Drop-in replacement — use your existing OpenAI SDK code, just change the base URL. If documents are uploaded, relevant context is… |
| GET |
listModels /v1/models |
List available models. Returns OpenAI-compatible model list. |
| Collections | ||
| GET |
listCollections /v1/collections |
List collections with aggregate stats (document count, chunk count, total tokens). |
| DELETE |
deleteCollection /v1/collections/{collection_id} |
Delete an entire collection and all its documents. Irreversible. |
| Monitoring | ||
| GET |
healthCheck /health |
Check API health and version. No authentication required. |
| GET |
getStats /v1/stats |
Monitor your usage: total documents, chunks, tokens, and capacity percentage. |
| Quality | ||
| POST |
verifyCitation /v1/verify |
Citation verification endpoint. Checks that AI-generated responses properly cite their sources. Detects uncited sentences, phantom citations (referencing non-existent sources),… |
| POST |
factCheck /v1/fact-check |
Standalone fact-checking endpoint. Extracts claims from text, verifies each against source context, and returns a verdict (verified/weak/rejected) with an actionable decision… |
| Analytics | ||
| GET |
getTrafficSummary /v1/analytics/traffic |
Per-tenant traffic statistics: requests today, tokens used, success rate, average latency, and P95 latency. Top 10 tenants by request volume. |
| GET |
getAnalytics /v1/analytics |
Cache performance, token savings, cost tracking, and system prompt deduplication metrics. The minutes parameter only affects cost metrics — cache, token, and dedup stats are… |
| GET |
getInsights /v1/insights |
Returns aggregated ROI metrics: token savings, estimated cost reduction, policy distribution, and validation latency. Track exactly how much value the pipeline delivers. |
| Other endpoints | ||
| GET |
getDocumentStatus /v1/documents/{document_id}/status |
Check the indexing status of an uploaded document. |
| POST |
uploadDocument /v1/upload |
Upload text content for RAG indexing. Max 10MB. |
| POST |
queryDocuments /v1/query |
Ask a question and get an answer with source citations. Max 2000 chars, top_k clamped to 10. Supports cost-aware routing via quality_mode parameter: "fast" (cheapest, simple… |
| POST |
Upload File /v1/upload-file |
Upload a file (text, image, PDF) via multipart form. Max 10 MB |
| POST |
uploadDocument /v1/upload |
Upload text content for RAG indexing. Automatically chunked for optimal retrieval. Max 10 MB, max 5000 chunks. |
| DELETE |
deleteDocument /v1/documents/{document_id} |
Delete a specific document and all its chunks. Irreversible. |
| POST |
uploadFile /v1/upload-file |
Upload a file (text, image, PDF) via multipart form. Supported: .txt, .md, .json, .yaml, .html, .rs, .py, .js, .ts, .png, .jpg, .gif, .webp. Max 10 MB. |
| GET |
getStats /v1/stats |
Monitor your usage: total documents, chunks, tokens, and capacity percentage. |
| GET |
healthCheck /health |
Check API health and version. No authentication required. |
| GET |
listDocuments /v1/documents |
List all indexed documents with metadata, chunk count, token count, and content preview. |
| DELETE |
deleteCollection /v1/collections/{collection_id} |
Delete an entire collection and all its documents. Irreversible. |
| GET |
listCollections /v1/collections |
List collections with aggregate stats (document count, chunk count, total tokens). |
| POST |
chatCompletions /v1/chat/completions |
OpenAI-compatible chat completions endpoint. Drop-in replacement — use your existing OpenAI SDK code, just change the base URL. If documents are uploaded, relevant context is… |
| GET |
listModels /v1/models |
List available models. Returns OpenAI-compatible model list. |
| POST |
queryDocuments /v1/query |
Ask a question and get an AI-generated answer with source citations and full audit trail. Uses hybrid retrieval (BM25 + semantic) with smart cost routing. |
| GET |
List Documents /v1/documents |
List all indexed documents in your knowledge base. Returns document IDs, chunk counts, token usage, and content previews. |
| DELETE |
Delete Document /v1/documents/{document_id} |
Delete a document and all its chunks. Automatically invalidates the query cache. Use the document_id returned by the upload endpoint. |
| GET |
List Collections /v1/collections |
List all collections with aggregate statistics: document count, chunk count, and total tokens. Each API key maps to one collection. |
| DELETE |
Delete Collection /v1/collections/{collection_id} |
Delete an entire collection and all its documents. Irreversible — all chunks are permanently removed and query cache is invalidated. |
| GET |
Usage Statistics /v1/stats |
Get real-time usage statistics: total documents, chunks, tokens, storage capacity, and collection count. Monitor your knowledge base size. |
| POST |
factCheck /v1/fact-check |
Standalone fact-checking endpoint. Extracts claims from text, verifies each against source context, and returns a verdict (verified/weak/rejected) with an actionable decision… |
| POST |
queryDocuments /v1/query |
Ask a question and get an AI-generated answer with source citations and full audit trail. Uses hybrid retrieval (BM25 + semantic) with smart cost routing. |
| GET |
getStats /v1/stats |
Monitor your usage: total documents, chunks, tokens, and capacity percentage. |
| GET |
healthCheck /health |
Check API health and version. No authentication required. |
| DELETE |
deleteDocument /v1/documents/{document_id} |
Delete a specific document and all its chunks. Irreversible. |
| POST |
uploadDocument /v1/upload |
Upload text content for RAG indexing. Automatically chunked for optimal retrieval. Max 10 MB, max 5000 chunks. |
| POST |
chatCompletions /v1/chat/completions |
OpenAI-compatible chat completions endpoint. Drop-in replacement — use your existing OpenAI SDK code, just change the base URL. If documents are uploaded, relevant context is… |
| POST |
uploadFile /v1/upload-file |
Upload a file (text, image, PDF) via multipart form. Supported: .txt, .md, .json, .yaml, .html, .rs, .py, .js, .ts, .png, .jpg, .gif, .webp. Max 10 MB. |
| GET |
listModels /v1/models |
List available models. Returns OpenAI-compatible model list. |
| GET |
listDocuments /v1/documents |
List all indexed documents with metadata, chunk count, token count, and content preview. |
| GET |
listCollections /v1/collections |
List collections with aggregate stats (document count, chunk count, total tokens). |
| DELETE |
deleteCollection /v1/collections/{collection_id} |
Delete an entire collection and all its documents. Irreversible. |
| GET |
getStats /v1/stats |
Monitor your usage: total documents, chunks, tokens, and capacity percentage. |
| GET |
healthCheck /health |
Check API health and version. No authentication required. |
+ 40 more endpoints on the provider's documentation.
Smart RAG API pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | — |
|
| PRO | $19 / month | 5 / second |
|
| ULTRA Recommended | $99 / month | 5 / second |
|
| MEGA | Free | 300 / second |
|
