Vespa is the AI Search Platform for fast, accurate and large scale RAG, personalization, and recommendation.
Vespa has garnered high praise from users, with frequent mentions of its functionality and user-friendliness, resulting in predominantly five-star reviews on platforms like G2. Users appreciate its capabilities, particularly in AI integration and performance, contributing to its strong reputation. However, there are occasional mentions of it being less well-known compared to other tools, though specifics about complaints are minimal. The pricing sentiment is not explicitly discussed in the available data, but the overall feedback is positive, with users displaying significant enthusiasm in social media, especially on platforms like YouTube.
Mentions (30d)
0
Avg Rating
4.6
8 reviews
Platforms
2
GitHub Stars
6,847
706 forks
Vespa has garnered high praise from users, with frequent mentions of its functionality and user-friendliness, resulting in predominantly five-star reviews on platforms like G2. Users appreciate its capabilities, particularly in AI integration and performance, contributing to its strong reputation. However, there are occasional mentions of it being less well-known compared to other tools, though specifics about complaints are minimal. The pricing sentiment is not explicitly discussed in the available data, but the overall feedback is positive, with users displaying significant enthusiasm in social media, especially on platforms like YouTube.
Features
Use Cases
Industry
information technology & services
Employees
69
Funding Stage
Series A
Total Funding
$31.0M
6,847
GitHub stars
20
npm packages
9
HuggingFace models
g2
What do you like best about Vespa?We purchased the Enclave product which was really well-suited for us because it let us run the hosts in our own Google cloud account (at our pricing with Google), and thus didn't require us to transfer any data out which was well-aligned with our security stance. It provided light-touch deployment and observability services that we lacked and helped us bootstrap quickly and with minimal investment. The Vespa search backend itself provided a good match to our requirements of near-real time hybrid search, combining nearest neighbor embedding search with attribute filters, in a distributed and highly scalable way. Our target installation comprised >12TB of memory across 24 hosts and held O(1B) vector embeddings. Review collected by and hosted on G2.com.What do you dislike about Vespa?Vespa, in a scalable deployment, presents a fairly complex architecture with a lot of tuning knobs and bells and whistles. It took several months to get familiar with them. The Vespa consultant was very instrumental in this. Feeding Vespa from BigQuery was harder than expected. Native extensions can only be written in Java which, without a native Java toolchain at our company, proved too challenging to pursue. The documentation is vast but could be better organized and have more contextual examples in places. Review collected by and hosted on G2.com.
What do you like best about Vespa?I like the open-source and free 300 dollar cloud credits for hosting the live applications. Review collected by and hosted on G2.com.What do you dislike about Vespa?I feel there should be more documentation work is in pending and needed as I am still exploring the AI and vector database part. Anyway I am happy to contribute for open source as a contributor. Review collected by and hosted on G2.com.
What do you like best about Vespa?I can create recommendation applications and deploy real-time machine learning inference using this stack. Such a level of functionality is what we need for our large scale search applications. Review collected by and hosted on G2.com.What do you dislike about Vespa?Vespa initialization and subsequent functioning, in fact, require a significant level of system configuration. It may be a little obscure sometimes and for troubleshooting issues one has to really appreciate the underlying environment. Review collected by and hosted on G2.com.
What do you like best about Vespa?The most helpful thing is the open source big data engine, heps to process and serve large scale data in real time with very low latency time.Its content recommendations are very useful for the modern day real-time analysis. Also, it is more flexible and scalable with advanced query techniques which makes it more easy to use. Review collected by and hosted on G2.com.What do you dislike about Vespa?Integrating vespa with existing systems and workflows can be challenging, particulary if systems were based on different technologies. Documentation and customer support for an open source is not at the top notch when compared to the real time products. since it is highly specialised it may overkill for simpler applications w or less demanding requirements. Review collected by and hosted on G2.com.
What do you like best about Vespa?For our use case in advertising, Vespa leaves Apache Lucene-based products in the dust: - High indexing throughput while searching - Very, very technical team - Best of the best technical support and guidance - Multiple times, discussions were had and the next day the idea was implemented Review collected by and hosted on G2.com.What do you dislike about Vespa?- Search is still costly - Improving ANN capabilities with ideas like DiskANN - Simplify schema configuration and testing - Lean in on more cloud native technologies Review collected by and hosted on G2.com.
What do you like best about Vespa?Vespa provides a comprehensive set of features you would look for in a search engine, particularly in more ranking capabilites (e.g. leveraging ML models) and performance than what Elasticsearch offers out of the box. They're also constantly making advancements in new capabilities that they offer a nice hybrid between vector databases and a conventional search engine. Particularly for our business problem at OkCupid of recommending potential matches to millions of other users based on a myriad of factors and ranking algorithms, Vespa was a great fit to not only meet those use cases, but improve our team's development and iteration workflows in our recs system. The Vespa team is also very active on Slack: https://vespatalk.slack.com/ssb/redirect and genuinely collaborative. In my case, we worked together with an engineer from their team who helped raise improvement changes into the engine to help us meet our use cases. Review collected by and hosted on G2.com.What do you dislike about Vespa?One of the challenges in the past was around documentation and general community knowledge and expertise. Their documentation has since gone through a substantial revamp Review collected by and hosted on G2.com.
What do you like best about Vespa?Powerful Search Capabilities: Vespa.ai's search engine delivers lightning-fast and highly relevant results, even for complex queries over vast datasets. Their advanced linguistics capabilities ensure accurate understanding of query intent. Scalable Architecture: I never have to worry about scaling with the Vespa cloud offering Rich Filtering and Ranking: Vespa provides extensive capabilities for filtering, ranking, and blending results based on multiple criteria and machine learning models. We leverage their HNSW and BM25 rankings Machine Learning Integration: Their tight integration with advanced machine learning frameworks like TensorFlow and PyTorch allows easy deployment of custom ML models for ranking, recommendations, and other use cases. Top Tier Customer Support: The Vespa team has been exceedingly responsive to my questions regarding how to implement certain features. Review collected by and hosted on G2.com.What do you dislike about Vespa?There can be a steep learning curve when onboarding to the product, though it is well worth the investment of time Review collected by and hosted on G2.com.
What do you like best about Vespa?Proven scalability with planet-scale deployments. Used internally at Yahoo. Self-hosted with docker and Kubernetes, or cloud hosted with autoscaling and automated updates. Deployment from configuration, with API or CLI. Vector search with self-hosted and remote embedding models. Hybrid search. Very powerful ranking language. Multi-stage: retrieval, ranking, reranking. Great support on GIthub. Review collected by and hosted on G2.com.What do you dislike about Vespa?The internal architecture is flexible but complex to master. Documentation used to be confusing, but is getting better. Review collected by and hosted on G2.com.
Repository Audit Available
Deep analysis of vespa-engine/vespa — architecture, costs, security, dependencies & more
Vespa uses a tiered pricing model. Visit their website for current pricing details.
Vespa has an average rating of 4.6 out of 5 stars based on 8 reviews from G2, Capterra, and TrustRadius.
Key features include: Vector, text and structured search, Machine learned ranking, Unbeatable performance, Infinite automated scalability, Continous deployment and upgrades, Fully managed with strong security.
Vespa is commonly used for: Real-time recommendation systems, Personalized content delivery, Search and retrieval in e-commerce platforms, Fraud detection in financial services, Dynamic ad placement and targeting, Natural language processing for chatbots.
Vespa integrates with: Apache Kafka, Kubernetes, Prometheus, Grafana, TensorFlow, PyTorch, Elasticsearch, Apache Spark, Jupyter Notebooks, RESTful APIs.

Vespa Now: 2026 Q1 Product Update
Mar 12, 2026
Vespa has a public GitHub repository with 6,847 stars.