The code for token cost calculation fails when using a LiteLLM proxy due to mismatch with the provider naming. For now, just handle this exception and assume cost 0 when that happens instead of breaking the flow - A more precise, LiteLLM proxy based cost calculation (relying in the `/model/info`) LiteLLM Proxy method will be needed
* Add gemini well-known-llm-provider
* Edit styling of anonymous function
* Remove space
* Edit how advanced options are displayed
* Add VertexAI to acceptable llm providers
* Add new `FileUploadFormField` component
* Edit FileUpload component
* Clean up logic for displaying native llm providers; add support for more complex `CustomConfigKey` types
* Fix minor nits in web app
* Add ability to pass vertex credentials to `litellm`
* Remove unused prop
* Change name of enum value
* Add back ability to change form based on first time configurations
* Create new Error with string instead of throwing raw string
* Add more Gemini models
* Edit mappings for Gemini models
* Edit comment
* Rearrange llm models
* Run black formatter
* Remove complex configurations during first time registration
* Fix nit
* Update llm provider name
* Edit temporary formik field to also have the filename
* Run reformatter
* Reorder commits
* Add advanced configurations for enabled LLM Providers
* WIP
* WIP almost done, but realized we can just do basic retrieval
* rebased and added scripts
* improved approach to extracting smart chips
* remove files from previous branch
* fix connector tests
* fix test
* Update web connector implementation and fix line length issues
* Update configurations and fix connector issues
* Update Slack connector
* Update connectors and add jira_test_env to gitignore, removing sensitive information
* Restore checkpointing functionality and remove sensitive information
* Fix agent mode to properly handle thinking tokens
* up
* Enhance ThinkingBox component with improved content handling and animations. Added support for partial thinking tokens, refined scrolling behavior, and updated CSS for better visual feedback during thinking states.
* Create clean branch with frontend thinking mode changes only
* Update ThinkingBox component to include new props for completion and streaming states. Refactor smooth scrolling logic into a dedicated function for improved readability. Add new entry to .gitignore for jira_test_env.
* Remove autoCollapse prop from AIMessage component for improved flexibility in message display.
* Update thinking tokens handling in chat utils
* Remove unused cleanThinkingContent import from Messages component to streamline code.
---------
Co-authored-by: ferdinand loesch <f.loesch@sportradar.com>
Co-authored-by: EC2 Default User <ec2-user@ip-10-73-128-233.eu-central-1.compute.internal>
Co-authored-by: Your Name <you@example.com>
Co-authored-by: Chris Weaver <25087905+Weves@users.noreply.github.com>
* working around a gong race condition in their api
* add back gong basic test
* formatting
* add the call index
---------
Co-authored-by: Richard Kuo (Onyx) <rkuo@onyx.app>
* add some gc
* small refactoring for temp directories
* WIP
* add some gc collects and size calculations
* un-xfail
* fix salesforce test
* loose check for number of docs
* adjust test again
* cleanup
* nuke directory param, remove using sqlite db to cache email / id mappings
---------
Co-authored-by: Richard Kuo (Onyx) <rkuo@onyx.app>
* Enhance Highspot connector with error handling and add unit tests for poll_source functionality
* Fix file extension validation logic to allow either plain text or document format
* gong debugging
* add retries via class level session, add debugging
* add gong connector test
---------
Co-authored-by: Richard Kuo (Onyx) <rkuo@onyx.app>
* add prometheus metrics endpoints via helper package
* model server specific requirements
* mark as public endpoint
---------
Co-authored-by: Richard Kuo (Onyx) <rkuo@onyx.app>
* fix large docs selected in chat pruning
* better approach to length restriction
* comments
* comments
* fix unit tests and minor pruning bug
* remove prints
* stubbing out request id
* passthru or create request id's in api and model server
* add onyx request id
* get request id logging into uvicorn
* no logs
* change prefixes
* fix comment
* docker image needs specific shared files
---------
Co-authored-by: Richard Kuo (Onyx) <rkuo@onyx.app>
* use slack's built in rate limit handler for the bot
* WIP
* fix the slack rate limit handler
* change default to 8
* cleanup
* try catch int conversion just in case
* linearize this logic better
* code review comments
---------
Co-authored-by: Richard Kuo (Onyx) <rkuo@onyx.app>
