35 Commits

Author	SHA1	Message	Date
Eradev	552a418bae	Merge branch 'staging' into staging-3071-v2	2025-01-28 10:49:53 -05:00
Cohee	4d18ddba6d	config.yaml: Group extension settings into one section	2025-01-17 20:18:27 +02:00
Eradev	1f9fa74786	Rewritten minLogLevel feature	2025-01-15 10:02:32 -05:00
Cohee	a0e6030836	Simplify node imports	2024-10-11 00:28:17 +03:00
Cohee	1616e7e067	Explicitly import Buffer. Specify jsdoc local extensions	2024-10-10 23:36:22 +03:00
Cohee	d52b4fbbde	Node: Migrate to ES Modules	2024-10-10 22:37:22 +03:00
Cohee	df3d7a048e	Deprecate unscoped vectors	2024-09-24 21:51:10 +03:00
Cohee	9ef3385255	Implement collection scopes for vector models (#2846) ... * Implement collection scopes for vector models * Update makersuite-vectors.js to use Gemini API text-embedding-004 model * Add model scope for Google vectors * Fix purge log * Refactor header setting * Fix typo * Only display UI warning if scopes disabled * Remove i18n attribute --------- Co-authored-by: ceruleandeep <83318388+ceruleandeep@users.noreply.github.com>	2024-09-16 09:29:39 +03:00
Cohee	8564d6faa8	Debug function to purge all vectors	2024-06-22 17:41:02 +03:00
Cohee	4e822eeebb	Add VLLM as vector source	2024-06-09 01:03:22 +03:00
Cohee	097894308e	#2328 Auto-regenerate corrupt vector indices	2024-05-29 14:53:55 +03:00
Cohee	2b3dfc5ae2	Add ollama and llamacpp as vector sources	2024-05-28 22:54:50 +03:00
Cohee	967a7980f5	Add vector retrieval score threshold	2024-05-23 17:28:43 +03:00
Cohee	25cb598694	Add Cohere as embedding source	2024-04-19 00:07:12 +03:00
Cohee	9a1ea7f226	Implement Data Bank vectors querying	2024-04-17 02:09:22 +03:00
Cohee	b07a6a9a78	Update all endpoints to use user directories	2024-04-07 01:47:07 +03:00
Cohee	5efdecc825	Add new OpenAI embedding models for selection	2024-03-12 21:41:30 +02:00
Kristian Schlikow	44a7dd3d74	Add NomicAI for vectorization (#1922) ... * Crudely add NomicAi for vectorization * Move NomicAI to its own endpoint, properly handle API key * Adjust clear button html * Remove leftover nomicai http header code * Revert changes to openai-vectors.js * Fix UI issues * Revert change to settings, fix UI --------- Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>	2024-03-12 21:10:25 +02:00
Kristan Schlikow	adfb9c5097	Implement TogetherAI as vectorization provider	2024-03-01 23:52:49 +01:00
Cohee	737a0bd3ae	Fix purge extras and mistral vectors	2024-02-23 22:37:00 +02:00
Cohee	c3129da879	[skip ci] Lint fix	2024-02-07 19:28:34 +02:00
Cohee	695b438c0d	Split vector batches into 10s	2024-02-01 11:02:47 +02:00
Juha Jeronen	6c8eff0544	Meh once more - use the name suggested in the review.	2024-01-24 16:08:38 +02:00
Juha Jeronen	bf3470411d	Meh, once more. Maybe better this way?	2024-01-24 16:04:29 +02:00
Juha Jeronen	915c238510	fix it correctly...	2024-01-24 16:03:04 +02:00
Juha Jeronen	91a688ee7f	oops, bug	2024-01-24 16:02:51 +02:00
Juha Jeronen	71344720d2	fix as per review	2024-01-24 16:02:08 +02:00
Juha Jeronen	0a07161cf8	support batch mode for Extras backend too	2024-01-24 15:48:14 +02:00
Juha Jeronen	a1c7e2918b	Merge branch 'staging' into vectordb-with-extras	2024-01-24 15:48:01 +02:00
Juha Jeronen	8b43535352	Initial support for Extras vectorizer, for Vector Storage	2024-01-24 15:16:55 +02:00
Cohee	cfdf43a26e	#1671 Add batch vectorization	2024-01-24 13:56:13 +02:00
based	5dd2e8cd88	added mistral vector support (off the back of oai's)	2023-12-16 08:37:39 +10:00
Cohee	d4f96020f2	Migrate Palm secret key, fix vector source key access	2023-12-14 19:33:23 +02:00
valadaptive	68049afd84	Use Express router for vectors endpoint	2023-12-04 13:01:52 -05:00
valadaptive	24546621e3	Move endpoints into their own folder	2023-12-04 10:12:27 -05:00