Skip to main content

​
Upsert Documents

Insert or update documents with your pre-computed vectors and JSON payload. Up to 1,000 documents per request. 
from mixpeek import Mixpeek

client = Mixpeek(api_key="sk_live_...")

result = client.namespaces.documents.upsert(
    namespace_id="product-search",
    documents=[
        {
            "document_id": "prod-001",
            "vectors": {"text_embedding": [0.12, -0.34, 0.56]},  # 1536 floats
            "payload": {"title": "Noise-Canceling Headphones", "price": 149.99, "in_stock": True},
        },
        {
            "document_id": "prod-002",
            "vectors": {"text_embedding": [0.08, 0.22, -0.41]},  # 1536 floats
            "payload": {"title": "Bluetooth Speaker", "price": 59.99, "in_stock": True},
        },
    ],
)
# → {"inserted": 2, "document_ids": ["prod-001", "prod-002"]}
Vector dimensions are validated against namespace config. If a document with the same ID exists, it is overwritten.

​
Bulk Import

For large datasets, stream NDJSON directly to shard WALs. Returns 202 Accepted with a batch ID to poll. 
curl -X POST "https://api.mixpeek.com/v1/namespaces/product-search/bulk-import" \
  -H "Authorization: Bearer $MIXPEEK_API_KEY" \
  -H "Content-Type: application/x-ndjson" \
  --data-binary @products.ndjson
products.ndjson
{"document_id": "prod-001", "vectors": {"text_embedding": [0.12, ...]}, "payload": {"title": "..."}}
{"document_id": "prod-002", "vectors": {"text_embedding": [0.08, ...]}, "payload": {"title": "..."}}

​
Dense (Vector)

results = client.search(
    namespace_id="product-search",
    queries=[{
        "vector_name": "text_embedding",
        "vector": query_embedding,
        "top_k": 10,
        "score_threshold": 0.7,
    }],
)

​
BM25 (Keyword)

Requires a text index on the target field. 
results = client.search(
    namespace_id="product-search",
    queries=[{"text": "wireless noise canceling", "top_k": 10}],
)

​
Sparse

results = client.search(
    namespace_id="product-search",
    queries=[{"sparse_vector": {42: 0.8, 1337: 0.5, 9001: 0.3}, "top_k": 10}],
)

​
Hybrid

Combine multiple query types with RRF or DBSF fusion. 
results = client.search(
    namespace_id="product-search",
    queries=[
        {"vector_name": "text_embedding", "vector": query_embedding, "top_k": 20},
        {"text": "wireless headphones", "top_k": 20},
    ],
    fusion="rrf",
)

​
Filtered

Add payload filters to any query type. Filters narrow results before scoring. 
results = client.search(
    namespace_id="product-search",
    queries=[{
        "vector_name": "text_embedding",
        "vector": query_embedding,
        "top_k": 10,
        "filters": {
            "must": [
                {"key": "price", "range": {"lte": 100}},
                {"key": "in_stock", "match": {"value": True}}
            ]
        },
    }],
)

​
Document Operations

OperationMethodEndpoint
Get by IDGET/v1/namespaces/{ns}/documents/{doc_id}
Update payloadPATCH/v1/namespaces/{ns}/documents/{doc_id}
DeleteDELETE/v1/namespaces/{ns}/documents/{doc_id}
Scroll (paginate)POST/v1/namespaces/{ns}/documents/scroll

​
Update Vectors

OperationMethodEndpoint
Replace vectors (single doc)PATCH/v1/namespaces/{ns}/documents/{doc_id}/vectors
Batch replace vectorsPOST/v1/namespaces/{ns}/documents/update-vectors
Add new vector indexPOST/v1/namespaces/{ns}/documents/add-vectors
Payload is untouched when updating vectors.