# Vector database for generative AI

> pgvector and Qdrant are nearly even for native vector search in generative AI applications in AI answers; neither question has a clear pick.

HTML: https://parse.gl/topics/vector-database-for-generative-ai · Site index: https://parse.gl/llms.txt

Market: [Developer Backend & Vector Search Services](https://parse.gl/markets/developer-backend-vector-search-services)

## Brands AI recommends

| Rank | Brand | Recommended |
| --- | --- | --- |
| #1 | Qdrant | 68% |
| #1 | pgvector | 67% |
| #1 | Weaviate | 64% |
| #4 | Pinecone | 58% |
| #4 | Milvus | 56% |
| #4 | PostgreSQL | 50% |
| #7 | MongoDB Atlas Vector Search | 41% |
| #8 | Mongodb | 28% |
| #9 | OpenSearch | 19% |
| #9 | Elasticsearch | 17% |
| #9 | Redis | 15% |
| #9 | Amazon Aurora | 14% |
| #9 | Oracle Database | 13% |
| #9 | Amazon OpenSearch Service | 13% |
| #15 | Zilliz Cloud | 11% |
| #15 | Azure Cosmos DB | 11% |
| #15 | Supabase | 10% |
| #15 | SingleStore | 10% |
| #15 | AlloyDB for PostgreSQL | 10% |
| #15 | Zilliz | 9% |
| #15 | Oracle | 9% |
| #15 | Microsoft SQL Server | 8% |
| #15 | Azure AI Search | 8% |
| #15 | MariaDB | 8% |
| #15 | Amazon DynamoDB | 7% |
| #15 | AWS | 6% |
| #15 | Couchbase | 6% |
| #15 | Apache Cassandra | 6% |
| #29 | Chroma | 5% |
| #29 | ClickHouse | 5% |
| #29 | LanceDB | 5% |
| #29 | Google Cloud SQL | 4% |
| #29 | Apache Doris | 4% |
| #29 | Oracle AI Vector Search | 4% |
| #29 | Vespa (Big Data Platform) | 4% |
| #29 | Redis Enterprise Cloud | 3% |
| #29 | Amazon RDS | 3% |
| #29 | Amazon S3 | 3% |
| #29 | Microsoft Azure | 3% |
| #29 | Turso | 3% |
| #29 | Azure SQL Database | 3% |
| #29 | Amazon Web Services | 3% |
| #29 | Amazon MemoryDB for Redis | 3% |
| #29 | Azure Database for PostgreSQL | 3% |
| #29 | DataStax Astra DB | 3% |
| #29 | TiDB Cloud | 3% |
| #29 | Qdrant Cloud | 3% |
| #29 | VAST DataBase | 3% |
| #29 | Neon | 2% |
| #29 | Google Cloud | 2% |
| #29 | Azure Blob Storage | 2% |
| #29 | Google Cloud Platform | 2% |
| #29 | Cloud Spanner | 2% |
| #29 | Google Cloud Storage | 2% |
| #29 | Cockroach Labs | 2% |
| #29 | Databricks | 2% |
| #29 | Digitalocean | 2% |
| #29 | Weaviate Cloud | 2% |
| #29 | FastAPI | 2% |
| #29 | MySQL HeatWave | 2% |
| #29 | Node.js | 2% |
| #29 | RediSearch | 2% |
| #29 | SAP HANA Cloud | 2% |
| #29 | SurrealDB | 2% |
| #65 | pgvectorscale | 1% |
| #65 | Elastic | 1% |
| #65 | Amazon OpenSearch Serverless | 1% |
| #65 | Amazon ElastiCache | 1% |
| #65 | Google Cloud Pub/Sub | 1% |
| #65 | Cloud Run | 1% |
| #65 | Cloudflare | 1% |
| #65 | Couchbase Vector Search | 1% |
| #65 | Databricks Mosaic AI | 1% |
| #65 | Datastax | 1% |
| #65 | Firebase | 1% |
| #65 | Fly | 1% |
| #65 | libSQL | 1% |
| #65 | MariaDB | 1% |
| #65 | Meta | 1% |
| #65 | Microsoft | 1% |
| #65 | Montycat | 1% |
| #65 | Neo4j | 1% |
| #65 | Next.js | 1% |
| #65 | OpenTelemetry | 1% |
| #65 | Oracle AI Native Database | 1% |
| #65 | React | 1% |
| #65 | Redis Cloud | 1% |
| #65 | Redis Stack | 1% |
| #65 | RisingWave | 1% |
| #65 | ScyllaDB | 1% |
| #65 | Turbopuffer | 1% |
| #65 | Valkey | 1% |
| #65 | Google Cloud Gemini Enterprise Agent Platform | 0% |
| #65 | Amazon Bedrock | 0% |
| #65 | Azure OpenAI Service | 0% |
| #65 | Weaviate Docs | 0% |
| #65 | Elastic Security | 0% |
| #65 | Facebook Research | 0% |
| #65 | GitHub | 0% |
| #65 | DiskANN | 0% |
| #65 | LlamaIndex | 0% |
| #65 | Marqo | 0% |
| #65 | MySQL | 0% |
| #65 | Neon | 0% |
| #65 | SQLite | 0% |
| #65 | Timescale | 0% |

## Questions

- I am looking for a database that supports vector search natively and does not require a separate bolt-on index.
- What infrastructure services are recommended for developing AI apps that require vector search capabilities and efficient data access?
- I want to avoid bolt-on indexes for vector search. What databases have this functionality built directly into the core?
- I need a database provider that offers native support for vector search to power a generative AI application.

## For agents

- [This page as data](https://parse.gl/api/public/topics/cloud-computing/developer-backend-vector-search-services/vector-database-for-generative-ai)
- [Every brand's share on this topic, with 95% ranges](https://agent.parse.gl/v1/tools/query_metrics?args=%7B%22measures%22%3A%5B%22share_named%22%5D%2C%22by%22%3A%5B%22brand%22%5D%2C%22filter%22%3A%7B%22topic%22%3A%5B%22top_1fa06cf3-16e3-4255-9b64-dd4f6453c907%22%5D%7D%7D)
- Search the index: `https://parse.gl/api/public/search?q=<words>`

Reuse: Figures and tables on this page are free to republish with attribution: a link to https://parse.gl/topics/vector-database-for-generative-ai beside them. A standard followed link (dofollow) is preferred.

- No account: Public figures and up to 5 examples per list, about 120 brands a day per address.
- Free account: $5 in credit, your brand's first check (20 buyer questions) and a free weekly check.
- After your first top-up: Exports and deeper search results. The first top-up starts at $5.
- Live checks: $0.01 per question per engine.
- Full public answers and pages: 25 free per day, then $0.005 each.
- Public answers older than 90 days: $0.001 each the first time your workspace counts or lists one, then yours.
- An agent can save work before signup: `POST https://agent.parse.gl/v1/workspaces`
- Connect an assistant: `https://agent.parse.gl/mcp`

[Prices](https://parse.gl/pricing.md) · [Map of the site](https://parse.gl/llms.txt)
