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

[Components] apipie_ai #13805

Open
pipedream-component-development opened this issue Sep 3, 2024 · 3 comments · May be fixed by #13862
Open

[Components] apipie_ai #13805

pipedream-component-development opened this issue Sep 3, 2024 · 3 comments · May be fixed by #13862
Assignees

Comments

@pipedream-component-development
Copy link
Collaborator

pipedream-component-development commented Sep 3, 2024

apipie_ai

URLs

Actions

chat

Prompt

Query LLM using text and, for vision-capable models, image data. Use reloadProps to change between chat completion and image completion.

URLs

text-to-speech

Prompt

Convert text to speech using the specified model and voice settings.

URLs

fetch-models

Prompt

Fetch all available models or use one or more filters

URLs

@jcortes jcortes self-assigned this Sep 3, 2024
@jcortes jcortes linked a pull request Sep 5, 2024 that will close this issue
@vunguyenhung
Copy link
Collaborator

Hello everyone, I have tested this PR and there're some test cases failed or needed improvement.

Please check the test report below for more information
https://vunguyenhung.notion.site/Components-apipie_ai-3e925dc9d5084e21b8535183699229e8

@jcortes
Copy link
Collaborator

jcortes commented Sep 9, 2024

Hi @vunguyenhung
Yes actually as far as I can tell there are issues on using the models they expose to the public, so these are the cases I found according to the QA evidence. I guess we should put this one as blocked in the meantime.

Request 1:

curl -X POST "https://apipie.ai/v1/chat/completions" \
-H "accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-pie7675580b5127eaaa3d3f609a59788411ac85252d37f3e70dbfc23e9ee59a8cfd" \
-d "{\"model\":\"llama-2-13b-chat,gemini-pro\",\"messages\":[{\"role\":\"assistan\",\"content\":\"You are an expert in weather forcast\"},{\"role\":\"user\",\"content\":\"How is the weather going to be for the next two days?\"},{\"role\":\"system\",\"content\":\"The anwser should only contain good insights\"}],\"max_tokens\":1000}"

Response 1:

{"error":"Internal server error"}

Request 2:

curl -X POST "https://apipie.ai/v1/audio/speech" \
-H "accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-pie7675580b5127eaaa3d3f609a59788411ac85252d37f3e70dbfc23e9ee59a8cfd" \
-d "{\"provider\":\"openai\",\"model\":\"tts-1-hd-1106\",\"input\":\"Today is a wonderful day to build something people love\",\"voice\":\"alloy\"}"

Response 2:

{"error":true,"message":"Missing audio or query details"}

@vunguyenhung
Copy link
Collaborator

Yeah I think we should put this one to blocked. Not making much sense to release actions that don't work

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Development

Successfully merging a pull request may close this issue.

3 participants