Skip to content
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

fix: flow trigger prompt + lower temp #2377

Merged
merged 2 commits into from
Oct 3, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions frontend/src/lib/components/copilot/flow.ts
Original file line number Diff line number Diff line change
Expand Up @@ -79,11 +79,11 @@ const triggerPrompts: {
python3: string
} = {
bun: `I'm building a workflow which is a sequence of script steps. Write the first script in {codeLang} which should check for {description} and return an array.
You can use "const {state_name}: {state_type} = await getState(...)" and "await setState(...)" from "windmill-client@1" to maintain state across runs.
You can use "const {state_name}: {state_type} = await getState()" and "await setState(value: any)" from "windmill-client@1" to maintain state across runs.

{additionalInformation}`,
python3: `I'm building a workflow which is a sequence of script steps. Write the first script in {codeLang} which should check for {description} and return an array.
You can use get_state and set_state from wmill to maintain state across runs.
You can use get_state() and set_state(value) from wmill to maintain state across runs.

{additionalInformation}`
}
Expand Down
2 changes: 1 addition & 1 deletion frontend/src/lib/components/copilot/lib.ts
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ import { buildClientSchema, printSchema } from 'graphql'
export const SUPPORTED_LANGUAGES = new Set(Object.keys(GEN_CONFIG.prompts))

const openaiConfig: CompletionCreateParamsStreaming = {
temperature: 0.3,
temperature: 0,
max_tokens: 2048,
model: 'gpt-4',
stream: true,
Expand Down
Loading
Loading