-
Notifications
You must be signed in to change notification settings - Fork 8.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Added a new optimized prompt for deepseek #5643
Closed
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
marcojsmith
commented
Jan 24, 2025
- add an additional option to the optimized prompt list for deepseek.
- updated the prompt for deekseep
Added a fav.ico
added a favicon.ico
…studio-fetch-warning fix: warn Constants Failed
…lazyRouteDiscovery-warn fix: update vite.config.ts
doc: update mkdocs.yml Bolt to bolt
used a consistent style throughout the mkdoc's when separating sections
checks to make sure the entered username and token is correct before accepting it. Let you disconnect also.
mkdoc consistent style
small update
new section heading added in index
Made links clickable in docs
Fix clickable links docs
Added and set a default provider icon
added and set a default provider icon
* fixed formatting of faq and enhanced styling * save * did further improvements and fixing the sidebar --------- Co-authored-by: Anirban Kar <[email protected]>
…anager component (stackblitz-labs#732) * fixed stackblitz-labs#333 * Added instruction in case api-key is not set. * addressed some of the review changes: 1. moved function definiton to useCallback. 2. added a cache to store the env key status and the api call is made only on a cache miss. * Manages the API-key entered via UI in a better way. - Persist API keys in cookies when entered via UI - Automatically load saved keys when switching between providers - Preserve existing functionality for environment variable based keys * Re-used map from utils/constants file. * Code cleanup - Removed redundant API key init in BaseChat as its already handled by APIKeyManager component.
chore: Update README.md with new model integration todo
Add Todo
…bs#1077) * fix: api-key manager cleanup and log error on llm call * log improved
…parency-about-development docs: document how we work
Co-authored-by: 刘一奇 <[email protected]>
* added the "Open Preview in a New Tab" * enhancement [Open Preview] [▼] // Two buttons side by side | +-- [Mobile (375x667)] // Dropdown menu |-- [Tablet (768x1024)] |-- [Laptop (1366x768)] +-- [Desktop (1920x1080)] * Update Preview.tsx * Update Preview.tsx
* Use backend API route to fetch dynamic models # Conflicts: # app/components/chat/BaseChat.tsx * Override ApiKeys if provided in frontend * Remove obsolete artifact * Transport api keys from client to server in header * Cache static provider information * Restore reading provider settings from cookie * Reload only a single provider on api key change * Transport apiKeys and providerSettings via cookies. While doing this, introduce a simple helper function for cookies
Environment variables are not being passed to the container in the development profile. Adding env_file to pass them so they can be used by the application.
- Enhanced text for bolt.diy docs section and better visibility to guide people there instead using github readme which is more for devs - added NodeJS based applications, as this is not clear and some people asked about in the community
…patch-readme-changes-v1 docs: update README.md
docs: replace docker-compose with docker compose
…VIEW_V3 fix: for Open preview in a new tab.
…abs#1139) * updated system prompt to have correct indentations * removed a section
fix: get environment variables for docker
…mplementing summary generation (stackblitz-labs#1091) #release * feat: add context annotation types and enhance file handling in LLM processing * feat: enhance context handling by adding chatId to annotations and implementing summary generation * removed useless changes * feat: updated token counts to include optimization requests * prompt fix * logging added * useless logs removed
I have added the option to select another optimized prompt, the deepseek prompt.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.