Commit graph

7 commits

Author SHA1 Message Date
Danny Avila
1a452121fa
🤖 feat: OpenAI Assistants v2 (initial support) (#2781)
* 🤖 Assistants V2 Support: Part 1

- Separated Azure Assistants to its own endpoint
- File Search / Vector Store integration is incomplete, but can toggle and use storage from playground
- Code Interpreter resource files can be added but not deleted
- GPT-4o is supported
- Many improvements to the Assistants Endpoint overall

data-provider v2 changes

copy existing route as v1

chore: rename new endpoint to reduce comparison operations and add new azure filesource

api: add azureAssistants part 1

force use of version for assistants/assistantsAzure

chore: switch name back to azureAssistants

refactor type version: string | number

Ensure assistants endpoints have version set

fix: isArchived type issue in ConversationListParams

refactor: update assistants mutations/queries with endpoint/version definitions, update Assistants Map structure

chore:  FilePreview component ExtendedFile type assertion

feat: isAssistantsEndpoint helper

chore: remove unused useGenerations

chore(buildTree): type issue

chore(Advanced): type issue (unused component, maybe in future)

first pass for multi-assistant endpoint rewrite

fix(listAssistants): pass params correctly

feat: list separate assistants by endpoint

fix(useTextarea): access assistantMap correctly

fix: assistant endpoint switching, resetting ID

fix: broken during rewrite, selecting assistant mention

fix: set/invalidate assistants endpoint query data correctly

feat: Fix issue with assistant ID not being reset correctly

getOpenAIClient helper function

feat: add toast for assistant deletion

fix: assistants delete right after create issue for azure

fix: assistant patching

refactor: actions to use getOpenAIClient

refactor: consolidate logic into helpers file

fix: issue where conversation data was not initially available

v1 chat support

refactor(spendTokens): only early return if completionTokens isNaN

fix(OpenAIClient): ensure spendTokens has all necessary params

refactor: route/controller logic

fix(assistants/initializeClient): use defaultHeaders field

fix: sanitize default operation id

chore: bump openai package

first pass v2 action service

feat: retroactive domain parsing for actions added via v1

feat: delete db records of actions/assistants on openai assistant deletion

chore: remove vision tools from v2 assistants

feat: v2 upload and delete assistant vision images

WIP first pass, thread attachments

fix: show assistant vision files (save local/firebase copy)

v2 image continue

fix: annotations

fix: refine annotations

show analyze as error if is no longer submitting before progress reaches 1 and show file_search as retrieval tool

fix: abort run, undefined endpoint issue

refactor: consolidate capabilities logic and anticipate versioning

frontend version 2 changes

fix: query selection and filter

add endpoint to unknown filepath

add file ids to resource, deleting in progress

enable/disable file search

remove version log

* 🤖 Assistants V2 Support: Part 2

🎹 fix: Autocompletion Chrome Bug on Action API Key Input

chore: remove `useOriginNavigate`

chore: set correct OpenAI Storage Source

fix: azure file deletions, instantiate clients by source for deletion

update code interpret files info

feat: deleteResourceFileId

chore: increase poll interval as azure easily rate limits

fix: openai file deletions, TODO: evaluate rejected deletion settled promises to determine which to delete from db records

file source icons

update table file filters

chore: file search info and versioning

fix: retrieval update with necessary tool_resources if specified

fix(useMentions): add optional chaining in case listMap value is undefined

fix: force assistant avatar roundedness

fix: azure assistants, check correct flag

chore: bump data-provider

* fix: merge conflict

* ci: fix backend tests due to new updates

* chore: update .env.example

* meilisearch improvements

* localization updates

* chore: update comparisons

* feat: add additional metadata: endpoint, author ID

* chore: azureAssistants ENDPOINTS exclusion warning
2024-05-19 12:56:55 -04:00
Danny Avila
e42709bd1f
🔍 feat: Show Messages from Search Result (#2699)
* refactor(Nav): delegate Search-specific variables/hooks to SearchContext

* fix: safely determine firstTodayConvoId if convo is undefined

* chore: remove empty line

* feat: initial render of search messages

* feat: SearchButtons

* update Ko.ts

* update localizations with new key phrases

* chore: localization comparisons

* fix: clear conversation state on searchQuery navigation

* style: search messages view styling

* refactor(Convo): consolidate logic to navigateWithLastTools from useNavigateToConvo

* fix(SearchButtons): styling and correct navigation logic

* fix(SearchBar): invalidate all message queries and invoke `clearText` if onChange value is empty

* refactor(NewChat): consolidate new chat button logic to NewChatButtonIcon

* chore: localizations for Nav date groups

* chore: update comparisons

* fix: early return from sendRequest to avoid quick searchQuery reset

* style: Link Icon

* chore: bump tiktoken, use o200k_base for gpt-4o
2024-05-14 11:00:01 -04:00
Danny Avila
1f0fb497f8
🎉 feat: Optimizations and Anthropic Title Generation (#2184)
* feat: add claude-3-haiku-20240307 to default anthropic list

* refactor: optimize `saveMessage` calls mid-stream via throttling

* chore: remove addMetadata operations and consolidate in BaseClient

* fix(listAssistantsForAzure): attempt to specify correct model mapping as accurately as possible (#2177)

* refactor(client): update last conversation setup with current assistant model, call newConvo again when assistants load to allow fast initial load and ensure assistant model is always the default, not the last selected model

* refactor(cache): explicitly add TTL of 2 minutes when setting titleCache and add default TTL of 10 minutes to abortKeys cache

* feat(AnthropicClient): conversation titling using Anthropic Function Calling

* chore: remove extraneous token usage logging

* fix(convos): unhandled edge case for conversation grouping (undefined conversation)

* style: Improved style of Search Bar after recent UI update

* chore: remove unused code, content part helpers

* feat: always show code option
2024-03-23 20:21:40 -04:00
Marco Beretta
911babd3e0
🖌️ style: Update Light/Dark UI Themes (#1754)
* BIG UI UPDATE

* fix: search bar, dialog template, new chat icon, convo icon and delete/rename button

* moved some color config and a lot of files

* small text fixes and tailwind config refactor

* Update localization and UI styles

* Update styles and add user-select:none to Tooltip component

* Update mobile.css styles for navigation mask and background color

* Update component imports and styles

* Update DeleteButton imports and references

* Update UI components

* Update tooltip delay duration

* Fix styling and update text in various components

* fixed assistant style

* minor style fixes

* revert: removed CreationHeader & CreationPanel

* style: match new styling for SidePanel

* style: match bg-gray-800 to ChatGPT (#212121)

* style: remove slate for gray where applicable to match new light theme

---------

Co-authored-by: Danny Avila <messagedaniel@protonmail.com>
2024-03-06 12:05:43 -05:00
Danny Avila
74459d6261
♾️ style: Infinite Scroll Nav and Sort Convos by Date/Usage (#1708)
* Style: Infinite Scroll and Group convos by date

* Style: Infinite Scroll and Group convos by date- Redesign NavBar

* Style: Infinite Scroll and Group convos by date- Redesign NavBar - Clean code

* Style: Infinite Scroll and Group convos by date- Redesign NavBar - Redesign NewChat Component

* Style: Infinite Scroll and Group convos by date- Redesign NavBar - Redesign NewChat Component

* Style: Infinite Scroll and Group convos by date- Redesign NavBar - Redesign NewChat Component

* Including OpenRouter and Mistral icon

* refactor(Conversations): cleanup use of utility functions and typing

* refactor(Nav/NewChat): use localStorage `lastConversationSetup` to determine the endpoint to use, as well as icons -> JSX components, remove use of `endpointSelected`

* refactor: remove use of `isFirstToday`

* refactor(Nav): remove use of `endpointSelected`, consolidate scrolling logic to its own hook `useNavScrolling`, remove use of recoil `conversation`

* refactor: Add spinner to bottom of list, throttle fetching, move query hooks to client workspace

* chore: sort by `updatedAt` field

* refactor: optimize conversation infinite query, use optimistic updates, add conversation helpers for managing pagination, remove unnecessary operations

* feat: gen_title route for generating the title for the conversation

* style(Convo): change hover bg-color

* refactor: memoize groupedConversations and return as array of tuples, correctly update convos pre/post message stream, only call genTitle if conversation is new, make `addConversation` dynamically either add/update depending if convo exists in pages already, reorganize type definitions

* style: rename Header NewChat Button -> HeaderNewChat, add NewChatIcon, closely match main Nav New Chat button to ChatGPT

* style(NewChat): add hover bg color

* style: cleanup comments, match ChatGPT nav styling, redesign search bar, make part of new chat sticky header, move Nav under same parent as outlet/mobilenav, remove legacy code, search only if searchQuery is not empty

* feat: add tests for conversation helpers and ensure no duplicate conversations are ever grouped

* style: hover bg-color

* feat: alt-click on convo item to open conversation in new tab

* chore: send error message when `gen_title` fails

---------

Co-authored-by: Walber Cardoso <walbercardoso@gmail.com>
2024-02-03 20:25:35 -05:00
Danny Avila
5145121eb7
feat(api): initial Redis support; fix(SearchBar): proper debounce (#1039)
* refactor: use keyv for search caching with 1 min expirations

* feat: keyvRedis; chore: bump keyv, bun.lockb, add jsconfig for vscode file resolution

* feat: api/search redis support

* refactor(redis) use ioredis cluster for keyv
fix(OpenID): when redis is configured, use redis memory store for express-session

* fix: revert using uri for keyvredis

* fix(SearchBar): properly debounce search queries, fix weird render behaviors

* refactor: add authentication to search endpoint and show error messages in results

* feat: redis support for violation logs

* fix(logViolation): ensure a number is always being stored in cache

* feat(concurrentLimiter): uses clearPendingReq, clears pendingReq on abort, redis support

* fix(api/search/enable): query only when authenticated

* feat(ModelService): redis support

* feat(checkBan): redis support

* refactor(api/search): consolidate keyv logic

* fix(ci): add default empty value for REDIS_URI

* refactor(keyvRedis): use condition to initialize keyvRedis assignment

* refactor(connectDb): handle disconnected state (should create a new conn)

* fix(ci/e2e): handle case where cleanUp did not successfully run

* fix(getDefaultEndpoint): return endpoint from localStorage if defined and endpointsConfig is default

* ci(e2e): remove afterAll messages as startup/cleanUp will clear messages

* ci(e2e): remove teardown for CI until further notice

* chore: bump playwright/test

* ci(e2e): reinstate teardown as CI issue is specific to github env

* fix(ci): click settings menu trigger by testid
2023-10-11 17:05:47 -04:00
Danny Avila
68ad46a9be
fix(typing): minor typing resolutions and convert SearchBar to TS (#766)
* refactor(SearchBar): convert to TS, useLocalize

* fix(typing): minor type issues

* chore(package.json): add 'reinstall:docker' script for rebuilding Docker environment in current branch
2023-08-06 21:30:16 -04:00
Renamed from client/src/components/Nav/SearchBar.jsx (Browse further)