Search that understands & responds
Free up to 15,000 queries, 15,000 generative requests per month, and 50 MB account size. ~20,000 pages of text; enough to load the entire Harry Potter series 5x.
A complete, secure, reliable and incredibly fast neural search platform
Grounded Generation |
||
---|---|---|
Generative AI summarization Summarized answers to your users’ questions are generated by our platform by first looking across all your data before responding. |
Good |
Best |
Hybrid search Provide the best answers to your users’ questions through search that is optimized to your data with a custom blend of large language model (LLM) based retrieval (i.e. "Semantic Search") and boolean exact match. |
Good |
Best |
Search and Indexing Features |
||
---|---|---|
Vectara Neural Rank™ Model for semantic search Neural model for document classification, retrieval, and ranking. |
||
Snippet extraction and highlighting Extract a snippet and highlight the relevant information from any retrieved document. |
||
Metadata annotation Extract file metadata such as document access control, source URI, document author, and other attributes. |
||
Confidence scores Get direct access to the ranking scores assigned by the platform. |
||
Neural re-ranking Neural model that re-ranks the top ranked documents for a given query. |
||
Direct file upload support Index documents in different file formats. |
||
Multi language search Index and search in multiple languages. |
||
Cross language search Search an index of a given language using queries in a different language. |
||
Custom dimensions Allow searches to be prioritized by customer-defined measures of relevance. |
||
Configurable data retention Submitted text data is not retained on Vectara for utmost data privacy. |
||
Search across multiple corpora Search across multiple indices or corpora at the same time. |
||
Usage analytics retention Access search and events analytics information. |
14 days |
90 days |
Resilience and Geographies |
||
---|---|---|
Replication for fault tolerance Improve fault tolerance, latency, and throughput of the service. |
||
Backups Configure backup retention to meet business needs. |
Security |
||
---|---|---|
Encryption at rest and in transit Protect data while stored and when moved between two services. |
||
Customer managed keys Customer ownership of the encryption keys that protect their data. |
Support & SLAs |
||
---|---|---|
Community Get support from user peers in a Vectara community forum. |
||
Email and website support Get support by contacting us directly via email or on our website. |
||
Premium support Designated hours to answer any question or help with any issue. |
Business hours |
|
Platform availability SLA Service level agreement defining the level of quality and availability of Vectara’s services. |
99%+ uptime guarantee |
|
Named support contacts (# of) Count of eligible creator(s) of support requests. |
3 |
|
Response times We make every reasonable effort to respond promptly. For production system outages, the target is within 1 hr. |
1 hour |
Quotas |
||
---|---|---|
Maximum Number of results per query The maximum number of results that will be returned for each query. |
100 |
500 |
Number of corpora (singular corpus) A corpus is a client-defined collection of data with a unique ID created via Vectara API or the Vectara Administrative Console. |
10 |
Up to 500,000 |
Number of users Allocated number of unique users within a customer account. |
5 |
Unlimited |
Number of admins Allocated number of users in a given account that can control user access and define account configurations. |
1 |
5 |
Size of reranker request The number of results that will be returned by a re-ranker request. |
25 |
100 |
Queries per month Number of queries that can be issued per month for the account. |
15,000 |
Contact Sales |
Generative requests per month Number of generative requests for summarizations that can be issued per month for the account. |
15,000 |
Contact Sales |
Account size Sum of size (measured in MB) of all corpora within the customer account after indexing, before any replication factor is applied. |
50 MB |
Contact Sales |
Ingest capacity Aggregate number of MB of data ingested via any supported Vectara ingest API. |
500 MB |
Contact Sales |
Additional 1,000 queries per month, 1,000 generative requests, and 5 MB incremental account size |
$1.25 per month |
Contact Sales |