Releases: devflowinc/trieve
Releases · devflowinc/trieve
v0.12.1
0.12.1 (2024-10-25)
Features
- /dataset/visiblity route to the server to set visibility with (ed2c4c0)
- add /topic/clone to the ts-sdk (8b6fe7e)
- add debounce for
getCounts,searchandsuggestedQueries(992d8cc) - add glasskube argocd app (afc7497)
- add group products checkmark to crawl settings (a4e23c7)
- add group variants flag (070a6a5)
- add ImageConfig for sending images to the llm (1f12579)
- add kustomization (9480d6d)
- add noResultsLink + styling: cleanup dark for active tab and search toggle (93a83f2)
- add noResultsLink + styling: cleanup dark for active tab and search toggle (84479c6)
- add open and onOpenChange as params for search component (cde5fa2)
- add packages kustomization (92ce2b0)
- add prices and images to ecomm chat (9097194)
- add search component example code (9b9d818)
- add shopify option to frontend (745d4ea)
- add shopify scraping (d3a6609)
- add site path to search results (60ad84a)
- add the ability to remove strings from titles and content during crawl (8517c98)
- add trieve hackernews application (9b5620e)
- add web component (4ca266c)
- added route to the backend for group_variants (6b2c7d5)
- added useImages to the frontend as a parameter (c2db61c)
- allow custom pre and post tags for highlights (c2f3777)
- allow for specifying allow_external_links and allow_backward_links (aeb9495)
- allow rag to use group search w/ a size of 1 (95debf6)
- allow user to specify that chunks' links should be included in generated output (baa9d39)
- authorization for webhook (e0c060c)
- auto focus input field (81a0567)
- bm25 settings when creating new dataset (e1346c7)
- change snake case to camel case (82035db)
- checkpoint where scraping of Trieve site + docs works correctly (a84bf93)
- clone topic and message route (4471cb8)
- clone topic in chat frontend (71c20d6)
- consistently link to the id anchor when possible from chunks in the search component, + cleanup: remove happy-dom (0f6ff50)
- create inital builderio webhook (c4d7ef2)
- create operator and impl system for content (3f472a4)
- delete applicationset (0e29e5a)
- docusarus theme plugin respects color scheme (2082bc3)
- docusaurus search plugin (6c1c393)
- event data explorer (a3303c6)
- fix button element position (23602b4)
- fixups and auth (2defca7)
- frontend page to toggle visibility + server dataset config for (78ea4d4)
- get all event types + bugfix: escape quotes properly for analytics (bc302dc)
- get page and deny access if no permission is given (8457683)
- group search in component (ea76b78)
- headless analytics (a59466d)
- jinja baseline (990aca5)
- json parsing (9810fae)
- lazy load search component (743a068)
- let embeddings share, gpu, update hash, increase splade-query doc memory (72dfab6)
- link custom events to actual events (c7724e5)
- make headings less noticable & extract heading heirarchy from chunks (6d08f4b)
- move package into folder (596740f)
- move to HEAD (8c0187d)
- new org modal in org select page (2250568)
- page.html renders template arguments passed through and react (646ec78)
- prevent switching modes (84c7039)
- properly shrink on page width decrease (f1f63e0)
- remove @radix-ui/react-dialog and downshift (90abf0a)
- remove kustomization (22175f0)
- remove syntax highlighting to reduce bundle size (28e51df)
- reverted previous code, added the rest needed for end to end (d84d6e1)
- send json blobs to llm for better parsing (5f5270b)
- set argocd source to pmig/trieve HEAD (5b0fd13)
- show first 3 lines of results (1943428)
- show vote score on dashboard rag table (8c97b2e)
- special logic to skip sending message to firecrawl (0ca6b5b)
- switch glasskube argocd deployment to main branch (46ee59b)
- unpublish (e0c060c)
- upgrade glasskube to v0.24.0 ([3c8661e](https://githu...
v0.12.0
0.12.0 (2024-10-07)
We put a lot of effort in this release to showcase all of the API features of Trieve in its many different forms. The high level features are:
- Better Analytics, as a first-class member in the dashboard 📈
- New Scraping support 🤖
- Search and Rag components ⚙
Analytics 📈
API Additions
- All llm based routes now return
TR-QueryIDthat allows you to enrich your own custom events. - Custom events are now first class and able to be queried with our events API
- Track events are now enabled for users, to track the full browser section end-to-end
Dashboard Additions
- Now displaying both RAG analytics and recommendations in the data explorer
- Now display Click Through Analytics first class in the Dashboard.
- CSV export
- button to register a custom search event in the dashboard.
commits:
- add ctr data to analytics page (2bc5a30)
- add CSV export support for all analytics (8c0b1bb)
- add llm response to rag analytics (aba46a1)
- Add routes to rate a RAG / Search Query (64657e9) (54fa779)
- add TR-QueryID to ALL llm response routes (62d9317)
- add track events for users (ee715fd)
- add top_score to recommendations-explorer (8170839)
- rag data explorer (791d687)
- recommendations explorer (f0a6fa1)
- get custom events with a metadata filter and move get CTR data under /events/ (9020e51)
Search Component ⚙
We created a search component that is fully integrated with all of the good features that Trieve has to offer. We feature both a chat widget and a search widget that can be easily plugged into your website
- add openapi crawl options (6bde73a)
- add suggested queries to search component (e7c4f80)
- add tags to search component (73640ee)
- add tanstack router to have new route for e commerce (c4acaff)
- allow stop generate when its loading (da56f5d)
- allow user to choose the key combination that opens the modal (3d268f2)
- allow user to pass suggested queries (fdb22d1)
- style openapi req verbs (19e5a2e)
New Scraping 🤖
We integrated with firecrawl to support scraping out of the box. This allows you to scrape your ecommerce store, personal blog, or openapi spec and instantly have an index for searching.
- Scrape any openapi.json to enrich the data crawl
- Generic scraping of any website of your choosing.
commits
- add OpenAPI specs to crawling setup (eb7a5db)
- add scraping config as an option to setup when creating a dataset (7a9f36c)
- add dataset event types for crawl success/fail (b6dca54)
- add TS instructions tab to get started code (43b69d2)
- dataset start checklist component for easier onboarding (68560aa)
- get crawl settings by dataset id (390e88e)
- show org+dataset selector on dataset page and change text to make dataset creation more obvious (928d4b5)
Enhancements
On Trieve Cloud we are now sending weekly and monthly updates to users about their usage with Trieve.
commits
- send to dittofeed on new user (271358e)
- add npm install command to trieve-ts-sdk (82d4bf0)
- various dashboard improvements like dataset selector bugfixes and better text in create dataset modal for info (bd4da07)
Bug Fixes
commits
- find not a function for dataset memo (a21096e)
- fix color vars for the outlines (3640949)
- fix cors error and allow TR-QueryId to be returned through CORS (94052ae)
- fix crawl worker docker push action (320301d)
- inconsistent page size for hybrid group search (b554c97)
- make sure to set current_chunk to correct one (31b586d)
- map not existing in NavbarDatasetSelector (8c6742b)
- more specific /api replacement on environment variable (378eed1)
- use rag_data to show results instead of search_data for RAG page (02c73e5)
- zod schema fixes broken dashboard layouts (f7992d8)
Docs
commits
- created quickstart development for search-component in readme (cb46473)
- created quickstart guide for working with the new analytics changes https://docs.trieve.ai/guides/analytics-quickstart
v0.11.9
0.11.9 (2024-09-20)
High level features
- Firecrawl doc searcher
Features
- add analytics link to playgrounds (3927f7c)
- add building something (696820a)
- add code examples (e8b7252)
- add copy button to chat (c35406d)
- add copy id button (75f218a)
- add created at sort in rag (7ad2d4d)
- add delete chunks flag to delete file route (3981811)
- add docker file and CI action to build scrape-worker (46039ca)
- add firecrawl to our docker compose (97deaa5)
- add org user page (806347c)
- add usage (863b7de)
- api keys (119b03d)
- api keys page (ffab74c)
- better api keys table (e8958fd)
- better sidebar (2fcbdf9)
- billing pages (c59da55)
- chunk on headings (1fde18a)
- consistent dataset context (aba6ed4)
- create org (c28a002)
- dataset overview (0cac1ab)
- dataset settings (7430e94)
- dataset sidebar with selector (9d2721a)
- dedup if url and page are the same (fdda50f)
- even better context (93e2b96)
- events page (887623e)
- fill in missing dates on graphs (2eca588)
- fix typo issues (590d808)
- fix usage (7de702a)
- included cron job in order to facilitate auto-scrapes (09edbae)
- init new console (daaa8fc)
- magic suspense (cc64d0a)
- magicbox (6e695a7)
- more magic box props (a845615)
- more on dataset homepage (f19c316)
- move crawl setting to dataset level (ae054f5)
- move to html chunking (51de3e1)
- move to polling firecrawl from webhook (649cb0b)
- new data explorer table (c350a5a)
- new dataset overview (90418e9)
- new tables for rag queries (48112ee)
- on update, create crawl if not exist (c844bba)
- org layout (6b9e07a)
- org settings page (d7c84de)
- org switching (dab332f)
- python client (5e864ee)
- redo table in no search query (dad2340)
- redo tables in search analytics (bbd7255)
- refactor user and invite tables (3f2494d)
- set up scrape worker with endpoint to crawl (0b472c2)
- set up semantic and full text boost for headings (332cd7c)
- simplify new org creation (fc677f4)
- update modal in data explorer (7c207a9)
- working dataset settings (79db3de)
Cleanup
- better CSS scoping for search component (87e847a)
- change default prompt such that LLM does not provide citations by default (6878f85)
- fix 2x typos of 'likeclickthrough' (4041788)
- improve pypi page for python sdk client (cd20b77)
- move towards html output from firecrawl (56f5c2b)
- properly handle fallback types for redis for Rust '24 version (6e14d18)
- put port back (1f21b1e)
- remove extra file (56da639)
- remove tooltip and globe icons (5831b53)
- update docker compose .env to include firecrawl (5404c91)
- update readme (aa46afb)
Bug Fixes
- add better margins to headings (868bc7c)
- add delete invitation to openapi spec (7a2b4c0)
- add get invitations to openapi spec (5f33336)
- auth edge cases (73b888d)
- concate short chunks to next one (d4dd68d)
- dataset warning for chat (82b8f21)
- ensure that dataset that is scrape to is the new dataset that is created (366380b)
- fill empty dates in rag usage chart (2537a6d)
- firecrawl scraping logic next behavior solve (c5103ab)
- fix copy feature to allow for plain text in chat (f4f2a2c)
- fix user cache flashing org select (505b5d8)
- no datasets warning for chat ([04a7775](0...
v0.11.8
Features
Created new TS-SDK #2214 #2253 #2265 #2287 https://ts-sdk.trieve.ai/
Created React Search Component #2261 #2278
Added Glasskube package manager #2272 #2266
Typo Tolerance #2263 #2273 #2275 #2283
Get Top Datasets #2252
UI Bugfixes
#2282
#2281
#2271
#2269
#2268
#2267
#2260
Analytics Improvements
Generic Events API #2251
Display multiquery events #2215
Bug Fixes
chunks get inserted in completion_first manner when completion_first = true #2245