-
-
Notifications
You must be signed in to change notification settings - Fork 1
feat:Update LemurTaskParams schema to include LemurBaseParams properties and fields #110
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
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -5644,13 +5644,50 @@ components: | |
| x-label: Prompt | ||
| description: Your text to prompt the model to produce a desired output, including any context you want to pass into the model. | ||
| type: string | ||
| required: [prompt] | ||
| - $ref: "#/components/schemas/LemurBaseParams" | ||
| transcript_ids: | ||
| x-label: Transcript IDs | ||
| description: | | ||
| A list of completed transcripts with text. Up to a maximum of 100 hours of audio. | ||
| Use either transcript_ids or input_text as input into LeMUR. | ||
| type: array | ||
| items: | ||
| x-label: Transcript ID | ||
| type: string | ||
| format: uuid | ||
| input_text: | ||
| x-label: Input text | ||
| description: | | ||
| Custom formatted transcript data. Maximum size is the context limit of the selected model. | ||
| Use either transcript_ids or input_text as input into LeMUR. | ||
| type: string | ||
| final_model: | ||
| x-label: Final model | ||
| description: | | ||
| The model that is used for the final prompt after compression is performed. | ||
| default: "default" | ||
| oneOf: | ||
| - $ref: "#/components/schemas/LemurModel" | ||
| max_output_size: | ||
| x-label: Maximum output size | ||
| description: Max output size in tokens, up to 4000 | ||
| type: integer | ||
| default: 2000 | ||
| temperature: | ||
|
Comment on lines
+5671
to
+5675
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more.
The duplicated field omits 🤖 Prompt for AI Agents |
||
| x-label: Temperature | ||
| description: | | ||
| The temperature to use for the model. | ||
| Higher values result in answers that are more creative, lower values are more conservative. | ||
| Can be any value between 0.0 and 1.0 inclusive. | ||
| type: number | ||
| format: float | ||
| default: 0 | ||
| minimum: 0 | ||
| maximum: 1 | ||
| required: [prompt, final_model] | ||
|
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. 💡 Verification agent 🧩 Analysis chainBreaking change: Existing clients may rely on If intentional, increment the API major version and document migration steps; otherwise restore the field via inheritance. 🏁 Script executed: #!/bin/bash
# Locate the /lemur/v3/generate/task endpoint and inspect its requestBody schema (showing 20 lines of context)
rg -n "/lemur/v3/generate/task" -C20 src/libs/AssemblyAI/openapi.yamlLength of output: 1665 🏁 Script executed: #!/bin/bash
# Inspect the LemurTaskParams schema to verify if 'context' was removed
rg -n "LemurTaskParams:" -C50 src/libs/AssemblyAI/openapi.yamlLength of output: 4448 Breaking change: The • File: src/libs/AssemblyAI/openapi.yaml Actions:
🤖 Prompt for AI Agents |
||
| example: | ||
| { | ||
| transcript_ids: ["64nygnr62k-405c-4ae8-8a6b-d90b40ff3cce"], | ||
| prompt: "List all the locations affected by wildfires.", | ||
| context: "This is an interview about wildfires.", | ||
| final_model: "anthropic/claude-sonnet-4-20250514", | ||
| temperature: 0, | ||
| max_output_size: 3000, | ||
|
|
||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
input_textduplicated & still optional – but now mutually exclusive rule vanishedinput_textduplicates the base definition and, more importantly, the prose rule “Use either transcript_ids or input_text” is no longer enforceable once inheritance is removed.Consider re-using
LemurBaseParamsor adding anoneOfcomposition to keep mutual-exclusivity machine-readable.🤖 Prompt for AI Agents