-
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
feat: add xAI model provider #10272
Merged
Merged
feat: add xAI model provider #10272
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
dosubot
bot
added
size:L
This PR changes 100-499 lines, ignoring generated files.
⚙️ feat:model-runtime
labels
Nov 5, 2024
crazywoola
approved these changes
Nov 5, 2024
BenjaminX
pushed a commit
to BenjaminX/ben-dify
that referenced
this pull request
Nov 5, 2024
Yeuoly
pushed a commit
that referenced
this pull request
Nov 5, 2024
Scorpion1221
added a commit
to yybht155/dify
that referenced
this pull request
Nov 5, 2024
* commit '7f583ec1ac6e7fb5269ed696f40a96a8b6b6f5fc': (176 commits) chore: update version to 0.11.0 across all relevant files (langgenius#10278) fix: iteration none output error (langgenius#10295) fix(http_request): improve parameter initialization and reorganize tests (langgenius#10297) fix typo: writeOpner to writeOpener (langgenius#10290) fix: handle KeyError when accessing rules in CleanProcessor.clean (langgenius#10258) fix: borken faq url in CONTRIBUTING.md (langgenius#10275) feat: add xAI model provider (langgenius#10272) feat(model_runtime): add new model 'claude-3-5-haiku-20241022' (langgenius#10285) fix(model_runtime): fix wrong max_tokens for Claude 3.5 Haiku on Amazon Bedrock (langgenius#10286) feat(model): add validation for custom disclaimer length (langgenius#10287) fix(node): correct file property name in function switch (langgenius#10284) refactor the logic of refreshing access_token (langgenius#10068) chore: translate i18n files (langgenius#10273) Updates: Add mplfonts library for customizing matplotlib fonts and Va… (langgenius#9903) feat: Iteration node support parallel mode (langgenius#9493) fix(workflow): handle else condition branch addition error in if-else node (langgenius#10257) feat(document_extractor): support tool file in document extractor (langgenius#10217) feat: support Claude 3.5 Haiku on Amazon Bedrock (langgenius#10265) refactor(parameter_extractor): implement custom error classes (langgenius#10260) fix: buitin tool aippt (langgenius#10234) ... # Conflicts: # .github/workflows/build-push.yml # api/Dockerfile # api/core/workflow/nodes/code/code_node.py
iamjoel
pushed a commit
that referenced
this pull request
Nov 7, 2024
AlwaysBluer
pushed a commit
to AlwaysBluer/dify
that referenced
this pull request
Nov 14, 2024
idonotknow
pushed a commit
to AceDataCloud/Dify
that referenced
this pull request
Nov 16, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Labels
⚙️ feat:model-runtime
lgtm
This PR has been approved by a maintainer
size:L
This PR changes 100-499 lines, ignoring generated files.
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.
Checklist:
Important
Please review the checklist below before submitting your pull request.
dev/reformat
(backend) andcd web && npx lint-staged
(frontend) to appease the lint godsDescription
Grok release their api yesterday, https://x.ai/blog/api
API Doc, https://docs.x.ai/api/endpoints
Close #7940
there are lots of error in xAI's doc, for example,
frequency_penalty
describe range as-2.0
to2.0
, but when you set to a negetive number, the API will raise error. And lots of missing, likemax_tokens
you can't get its value, and all the parameters you don't know its default value.Type of Change
Testing Instructions
test locally and run unittest.