Pinecone full-text (BM25) search and Documents API are now GA

What you get

As of 2026-09-02, full-text search is generally available on Pinecone API version 2026-07, built on the new Documents API, so one index can combine BM25, dense-vector and sparse-vector fields and match exact terms like SKUs, IDs and error codes.

Prerequisites

Pinecone Python SDK v10 or later (required for 2026-07 schema-based indexes)
A Pinecone API key from https://app.pinecone.io
Note: on 2026-07, POST /indexes is schema-only (a schema object replaces top-level params). Existing indexes and SDK create_index calls are unaffected.

Steps

Install and set your key:

Shell

pip install --upgrade pinecone
export PINECONE_API_KEY="YOUR_API_KEY"

Create an index with a full-text field:

Python

import os, time
from pinecone import Pinecone, SchemaBuilder

pc = Pinecone(api_key=os.environ["PINECONE_API_KEY"])

schema = (
    SchemaBuilder()
      .add_string_field(name="text", full_text_search={"language": "en"})
      .build()
)
if not pc.indexes.exists(name="quickstart"):
    pc.indexes.create(name="quickstart", schema=schema)

while not pc.indexes.describe(name="quickstart").status.ready:
    time.sleep(2)

index = pc.Index(name="quickstart")

Upsert documents:

Python

index.documents.upsert(
    namespace="__default__",
    documents=[
        {"_id": "1", "text": "SKU KB-1024: wireless mechanical keyboard, USB-C, brown switches", "category": "product"},
        {"_id": "2", "text": "SKU MON-4200: 27-inch 4K monitor, HDMI and USB-C", "category": "product"},
        {"_id": "3", "text": "Order 88231 shipped on 2026-08-20 via express courier", "category": "order"},
        {"_id": "4", "text": "Error E1042: connection timeout after 30 seconds", "category": "log"},
        {"_id": "5", "text": "Ticket 5567 resolved: replaced faulty power adapter", "category": "support"},
    ],
)

time.sleep(5)

Run a BM25 search:

Python

resp = index.documents.search(
    namespace="__default__",
    top_k=3,
    score_by=[{"type": "text", "fields": ["text"], "query": "E1042"}],
    include_fields=["*"],
)

for m in resp.matches:
    print(m._id, m._score, getattr(m, "text", ""))

Test it

Document 4 (Error E1042: connection timeout...) should be the top match. Follow-up: since 2026-07-21 full-text search also supports fuzzy matching and n-grams for typos and substrings.