> ## Documentation Index > Fetch the complete documentation index at: https://docs.mixpeek.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Retrieval Cookbook > Ready-to-copy, runnable multi-stage retriever configurations for common multimodal patterns Retrieval cookbook: ready-to-copy pipeline recipes for RAG, hybrid search, video moments, face search, and dedup Every recipe below is a complete, copy-paste retriever config. Create the retriever once, then execute it with runtime `inputs`. **Stage shape.** Every stage is `{ "stage_name", "stage_type", "config": { "stage_id", "parameters" } }`. `stage_name` is your label; `stage_id` is the implementation (`feature_search`, `rerank`, `attribute_filter`, …); `stage_type` is the category (`filter`, `sort`, `reduce`, `group`, `enrich`, `apply`). See [Retrievers](/retrieval/retrievers) and [Stages](/retrieval/stages/overview). **Point `feature_uri` at *your* collection's index.** Each recipe's `feature_search` uses a `feature_uri` for a specific extractor (e.g. `mixpeek://multimodal_extractor@v1/vertex_multimodal_embedding`). That string must match the collection you built — a `video_search` collection uses `mixpeek://universal_extractor@v1/gemini-embedding-2`, **not** the multimodal one. A mismatched `feature_uri` silently returns **0 results**. Find yours with `GET /v1/collections/{id}` → `vector_indexes[].feature_uri` — see [Find your feature\_uri](/processing/features#find-your-feature_uri-to-search). ```bash Create + execute (every recipe uses this) theme={null} # Create the retriever (body = one of the recipes below) curl -sS -X POST "$MP_API_URL/v1/retrievers" \ -H "Authorization: Bearer $MP_API_KEY" -H "X-Namespace: $MP_NAMESPACE" \ -H "Content-Type: application/json" -d @recipe.json # -> returns { "retriever_id": "ret_..." } # Execute it with runtime inputs curl -sS -X POST "$MP_API_URL/v1/retrievers/{retriever_id}/execute" \ -H "Authorization: Bearer $MP_API_KEY" -H "X-Namespace: $MP_NAMESPACE" \ -H "Content-Type: application/json" \ -d '{ "inputs": { "query": "people discussing electric vehicles" } }' ``` *** ## Multimodal RAG Retrieve context for an LLM across a video's **visual** content and **transcript**, fuse with RRF, rerank, and format into a single prompt-ready context block. ```json theme={null} { "retriever_name": "multimodal-rag", "collection_identifiers": ["col_videos"], "input_schema": { "query": { "type": "text", "required": true } }, "stages": [ { "stage_name": "search", "stage_type": "filter", "config": { "stage_id": "feature_search", "parameters": { "fusion": "rrf", "final_top_k": 50, "searches": [ { "feature_uri": "mixpeek://multimodal_extractor@v1/vertex_multimodal_embedding", "query": { "input_mode": "text", "value": "{{INPUT.query}}" }, "top_k": 100 }, { "feature_uri": "mixpeek://multimodal_extractor@v1/multilingual_e5_large_instruct_v1", "query": { "input_mode": "text", "value": "{{INPUT.query}}" }, "top_k": 100 } ] } } }, { "stage_name": "rerank", "stage_type": "sort", "config": { "stage_id": "rerank", "parameters": { "inference_name": "BAAI__bge_reranker_v2_m3", "query": "{{INPUT.query}}", "top_k": 10 } } }, { "stage_name": "prepare", "stage_type": "apply", "config": { "stage_id": "rag_prepare", "parameters": { "max_tokens": 8000, "output_mode": "single_context", "citation": { "style": "numbered" } } } } ] } ``` **Result:** the 10 most relevant moments, reranked, formatted into a cited context block ready to paste into an LLM prompt. *** ## Hybrid Search (dense + keyword/BM25) Fuse semantic recall (dense vectors) with exact-keyword precision (BM25) under RRF — so brand names, SKUs, and prices like `$9.99` still match. Requires a `text` payload index (see [Text Indexes](/vector-store/namespaces#text-indexes-bm25)). ```json theme={null} { "retriever_name": "hybrid-search", "collection_identifiers": ["col_docs"], "input_schema": { "query": { "type": "text", "required": true } }, "stages": [ { "stage_name": "hybrid", "stage_type": "filter", "config": { "stage_id": "feature_search", "parameters": { "fusion": "rrf", "final_top_k": 25, "searches": [ { "feature_uri": "mixpeek://text_extractor@v1/multilingual_e5_large_instruct_v1", "query": { "input_mode": "text", "value": "{{INPUT.query}}" }, "top_k": 100 }, { "feature_uri": "mixpeek://text_extractor@v1/multilingual_e5_large_instruct_v1", "query": { "input_mode": "text", "value": "{{INPUT.query}}" }, "lexical": true, "top_k": 100 } ] } } } ] } ``` **Result:** 25 results ranked by fused semantic + keyword relevance. Use `rrf` here — it ranks by position, immune to the cosine-vs-BM25 score-scale mismatch. *** ## Search Across Languages (cross-lingual) Mixpeek's text and multimodal embeddings are **multilingual** (E5-Large / Gemini, 100+ languages) and every language lands in the **same** vector space. So a query in one language retrieves semantically matching content in **any** language — no translation step, no per-language index, no language parameter. Query in English, match Farsi, Mandarin, or Spanish transcripts and captions. ```json theme={null} { "retriever_name": "cross-lingual-search", "collection_identifiers": ["col_content"], "input_schema": { "query": { "type": "text", "required": true } }, "stages": [ { "stage_name": "search", "stage_type": "filter", "config": { "stage_id": "feature_search", "parameters": { "final_top_k": 25, "searches": [ { "feature_uri": "mixpeek://text_extractor@v1/multilingual_e5_large_instruct_v1", "query": { "input_mode": "text", "value": "{{INPUT.query}}" }, "top_k": 100 } ] } } } ] } ``` **Result:** an English query like `"discussion of sanctions"` returns segments whose transcript or caption is in another language — ranked by meaning, not keywords. For **audio/video** collections, transcription is produced in the **source** language ([universal](/processing/extractors/universal) / [audio](/processing/extractors/audio-sentiment) extractors; Whisper covers 99 languages) and the multilingual embedding is what makes it retrievable cross-lingually — just point `feature_uri` at that extractor's transcript embedding, e.g. `mixpeek://multimodal_extractor@v1/multilingual_e5_large_instruct_v1`. **Mixpeek retrieves across languages; it does not translate.** There is no translation output field — matched text comes back in its **original language**. If you need it rendered in the reader's language (e.g. original + English side by side), append an [`llm_enrich`](/retrieval/stages/llm-enrich) stage that translates each result into a new field: ```json theme={null} { "stage_name": "translate", "stage_type": "enrich", "config": { "stage_id": "llm_enrich", "parameters": { "provider": "openai", "model_name": "gpt-4o-mini", "prompt": "Translate the following to English, preserving names and numbers. Return only the translation:\n\n{{DOC.content}}", "output_field": "translation" } } } ``` Each result then carries both `content` (original) and `translation` (English) for side-by-side display. This is the recommended path — reach for a [custom extractor](/processing/custom-extractors) only if you need translation baked in at ingest time. *** ## Video Moment Localization Search a video and collapse matching segments into a handful of seekable moments with start/end timestamps. ```json theme={null} { "retriever_name": "video-moments", "collection_identifiers": ["col_videos"], "input_schema": { "query": { "type": "text", "required": true } }, "stages": [ { "stage_name": "search", "stage_type": "filter", "config": { "stage_id": "feature_search", "parameters": { "final_top_k": 200, "searches": [ { "feature_uri": "mixpeek://multimodal_extractor@v1/vertex_multimodal_embedding", "query": { "input_mode": "text", "value": "{{INPUT.query}}" }, "top_k": 200 } ] } } }, { "stage_name": "moments", "stage_type": "reduce", "config": { "stage_id": "moment_group", "parameters": { "parent_field": "source_object_id", "time_field": "start_time", "merge_tolerance_ms": 2000, "max_moments_per_parent": 5, "score_strategy": "max", "output_mode": "annotated" } } } ] } ``` **Result:** per video, up to 5 merged moments with timestamps you can seek to. `time_field` must point at the field holding each segment's timestamp. For a plain **text** query use the segment's own `start_time`. `query_chunks` is only present when you search with a **file** input via [query preprocessing](/retrieval/stages/feature-search#query-preprocessing). *** ## Face Search (1:N identification) Find every clip a person appears in by passing a reference face image as a `content` query against the face embedding. ```json theme={null} { "retriever_name": "face-search", "collection_identifiers": ["col_videos"], "input_schema": { "reference_face_url": { "type": "text", "required": true } }, "stages": [ { "stage_name": "face", "stage_type": "filter", "config": { "stage_id": "feature_search", "parameters": { "final_top_k": 20, "searches": [ { "feature_uri": "mixpeek://face_identity_extractor@v1/insightface__arcface", "query": { "input_mode": "content", "value": "{{INPUT.reference_face_url}}" }, "top_k": 50 } ] } } } ] } ``` **Result:** the 20 closest face matches. A cosine score above \~0.30 typically indicates the same person (see [Face Identity](/processing/extractors/face-identity)). This recipe chases **one** reference face. To match every new video against a maintained **roster of named identities** (a watchlist you add to and refine over time), build a reference collection instead — see [Bootstrap a Labeled Dataset](/tutorials/bootstrap-labeled-dataset). *** ## Reverse Image Search + Dedup Find visually similar items from *other* sources, deduplicated. ```json theme={null} { "retriever_name": "reverse-image", "collection_identifiers": ["col_catalog"], "input_schema": { "image_url": { "type": "text", "required": true }, "exclude_source": { "type": "text" } }, "stages": [ { "stage_name": "similar", "stage_type": "filter", "config": { "stage_id": "feature_search", "parameters": { "final_top_k": 100, "searches": [ { "feature_uri": "mixpeek://image_extractor@v1/google_siglip_base_v1", "query": { "input_mode": "content", "value": "{{INPUT.image_url}}" }, "top_k": 100, "min_score": 0.7 } ] } } }, { "stage_name": "exclude_self", "stage_type": "filter", "config": { "stage_id": "attribute_filter", "parameters": { "field": "metadata.source", "operator": "ne", "value": "{{INPUT.exclude_source}}" } } }, { "stage_name": "dedupe", "stage_type": "reduce", "config": { "stage_id": "deduplicate", "parameters": { "strategy": "field", "fields": ["metadata.source_url"], "keep": "first" } } } ] } ``` **Result:** unique visually-similar items, excluding the original source. *** ## Search OCR Text from Scanned PDFs Scanned and archival PDFs are OCR'd — and VLM-corrected for low-confidence blocks — by the [document graph extractor](/processing/extractors/document), which embeds each text block. So OCR'd text is searchable exactly like any other text: no separate OCR index or step. Optionally keep only high-confidence blocks, or target a layout type (e.g. only `table` blocks). ```json theme={null} { "retriever_name": "ocr-search", "collection_identifiers": ["col_scanned_docs"], "input_schema": { "query": { "type": "text", "required": true } }, "stages": [ { "stage_name": "search", "stage_type": "filter", "config": { "stage_id": "feature_search", "parameters": { "final_top_k": 25, "searches": [ { "feature_uri": "mixpeek://document_graph_extractor@v1/intfloat__multilingual_e5_large_instruct", "query": { "input_mode": "text", "value": "{{INPUT.query}}" }, "top_k": 100 } ] } } }, { "stage_name": "high_confidence", "stage_type": "filter", "config": { "stage_id": "attribute_filter", "parameters": { "field": "confidence_tag", "operator": "in", "value": ["A", "B"] } } } ] } ``` **Result:** the 25 best-matching blocks (each with `page_number`, `bbox`, `object_type`), limited to high-confidence OCR. Drop the `high_confidence` stage to include fair/poor blocks, or filter `object_type` to `table`/`form` to target structured regions. For text burned into **video frames** (not PDFs), enable `run_ocr` on the [multimodal extractor](/processing/extractors/multimodal) — it populates an `ocr_text` payload field you can filter on with [`attribute_filter`](/retrieval/stages/attribute-filter). See also [feature\_search → Lexical (BM25)](/retrieval/stages/feature-search#lexical-bm25-search). *** ## Search + Classify Search, then attach an LLM/taxonomy label to each result in one pipeline. ```json theme={null} { "retriever_name": "search-classify", "collection_identifiers": ["col_content"], "input_schema": { "query": { "type": "text", "required": true } }, "stages": [ { "stage_name": "search", "stage_type": "filter", "config": { "stage_id": "feature_search", "parameters": { "final_top_k": 25, "searches": [ { "feature_uri": "mixpeek://multimodal_extractor@v1/vertex_multimodal_embedding", "query": { "input_mode": "text", "value": "{{INPUT.query}}" }, "top_k": 100 } ] } } }, { "stage_name": "label", "stage_type": "enrich", "config": { "stage_id": "llm_enrich", "parameters": { "provider": "openai", "model_name": "gpt-4o-mini", "prompt": "Classify this result: {{DOC.content}}", "output_field": "label", "output_schema": { "category": "string", "confidence": "number" } } } } ] } ``` **Result:** 25 results, each annotated with a structured `label`. For NSFW/safety classification use the [`classify`](/retrieval/stages/classify) stage; for taxonomy-backed labeling see [Taxonomies](/enrichment/taxonomies). *** ## Scan a batch of inputs Any retriever can run many queries at once — ideal for moderating an upload queue or scanning a catalog: ```bash theme={null} curl -sS -X POST "$MP_API_URL/v1/retrievers/{retriever_id}/execute/batch" \ -H "Authorization: Bearer $MP_API_KEY" -H "X-Namespace: $MP_NAMESPACE" \ -H "Content-Type: application/json" \ -d '{ "queries": [ {"inputs": {"image_url": "https://…/a.jpg"}}, {"inputs": {"image_url": "https://…/b.jpg"}} ] }' ``` The retriever is planned once and reused across the batch ([query optimization](/retrieval/query-optimization)). ## Composing recipes Stages are independent — add, remove, or reorder them. Common extensions: append a [`rerank`](/retrieval/stages/rerank) for precision, an [`attribute_filter`](/retrieval/stages/attribute-filter) for metadata scoping (the optimizer pushes it down for you), or a [`rag_prepare`](/retrieval/stages/rag-prepare) to format for an LLM.