OpenAI
This OpenAI app in Blackbird grants you access to all API endpoints and models that OpenAI has to offer from completion, chat, edit to DALL-E image generation and Whisper.
Before setting up
Before you can connect you need to make sure that:
- You have an OpenAI account and organization and have access to the API keys.
Connecting
- Navigate to apps and search for OpenAI. If you cannot find OpenAI then click Add App in the top right corner, select OpenAI and add the app to your Blackbird environment.
- Click Add Connection.
- Name your connection for future reference e.g. ‘My OpenAI connection’.
- Fill in your Organization ID that you can find in your OpenAI organization settings. The organization ID has the shape
org-xxxxxxxxxxxxxxxxxxxxxxxx. - Fill in your API key. You can create a new API key under API keys. The API key has the shape
sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx. - Click Connect.
Actions
All textual actions have the following optional input values in order to modify the generated response:
- Model (defaults to the latest)
- Maximum tokens
- Temperature
- top_p
- Presence penalty
- Frequency penalty
For more in-depth information about most actions consult the OpenAI API reference.
Be aware that model parameter’s dynamic input returns all available models. You should select the model that is appropriate for the given task (e.g. gpt-4 model for Chat action). Action groups and models that should be used for them are shown in the table below.
| Action group | Latest models | Deprecated models |
|---|---|---|
| Chat | gpt-4 and dated model releases, gpt-4-1106-preview, gpt-4-vision-preview, gpt-4-32k and dated model releases, gpt-3.5-turbo and dated model releases, gpt-3.5-turbo-16k and dated model releases, fine-tuned versions of gpt-3.5-turbo | gpt-3.5-turbo-0613, gpt-3.5-turbo-16k-0613, gpt-3.5-turbo-0301, gpt-4-0314, gpt-4-32k-0314 |
| Completions | gpt-3.5-turbo-instruct, babbage-002, davinci-002 | text-ada-001, text-babbage-001, text-curie-001, text-davinci-001, text-davinci-002, text-davinci-003 |
| Audiovisual | Only whisper-1 is supported for transcriptions and translations. tts-1 and tts-1-hd are supported for speech creation. | - |
| Images | dall-e-2, dall-e-3 | - |
| Embeddings | text-embedding-ada-002 | text-similarity-ada-001, text-similarity-babbage-001, text-similarity-curie-001, text-similarity-davinci-001, text-search-ada-doc-001, text-search-ada-query-001, text-search-babbage-doc-001, text-search-babbage-query-001, text-search-curie-doc-001, text-search-curie-query-001, text-search-davinci-doc-001, text-search-davinci-query-001, code-search-ada-code-001, code-search-ada-text-001, code-search-babbage-code-001, code-search-babbage-text-001 |
You can refer to the Models documentation to find information about available models and the differences between them.
Some actions that are offered are pre-engineered on top of OpenAI. This means that they extend OpenAI’s endpoints with additional prompt engineering for common language and content operations.
Do you have a cool use case that we can turn into an action? Let us know!
Chat
- Chat given a chat message, returns a response.
- Chat with system prompt same as above but with an extra instructional system prompt parameter.
- Chat with image provides response given a chat message and image.
- Generate edit edits the provided text given an instruction.
- Chat with image provides response given a chat message and image.
- Post-edit MT (Pre-engineered) given a source segment and NMT translated target segment, responds with a post-edited version of the target segment taking into account typical NMT mistakes.
- Get translation issues (Pre-engineered) given a source segment and NMT translated target segment, highlights potential translation issues. Can be used to prepopulate TMS segment comments.
- Get MQM report (Pre-engineered) performs an LQA Analysis of the translation. The result will be in the MQM framework form. The dimensions are: terminology, accuracy, linguistic conventions, style, locale conventions, audience appropriateness, design and markup. The input consists of the source and translated text. Optionally one can add languages and a description of the target audience.
- Get MQM dimension values (Pre-engineered) uses the same input and prompt as ‘Get MQM report’. However, in this action the scores are returned as individual numbers so that they can be used in decisions. Also returns the proposed translation.
- Translate text (Pre-engineered) given a text and a locale, tries to create a localized version of the text.
- Get localizable content from image retrieves localizable content from given image.
Completions
- Generate completion generates a completion of the given text.
- Create summary (Pre-engineered) given a text, generates a summary.
Edits
- Generate edit Given a text and an instruction, edits the given text.
Audiovisual
- Create transcription transcribes the supported audiovisual file formats into a textual response.
- Create English translation same as above but automatically translated into English.
- Create speech generates audio from the text input.
Images
- Generate image use DALL-E to generate an image based on a prompt.
Other
- Create embedding create a vectorized embedding of a text. Useful in combination with vector databases like Pinecone in order to store large sets of data.
- Tokenize text turn a text into tokens. Uses Tiktoken under the hood.
Example
This simple example how OpenAI can be used to communicate with the Blackbird Slack app. Whenever the app is mentioned, the message will be send to Chat to generate an answer. We then use Amazon Polly to turn the textual response into a spoken-word resopnse and return it in the same channel.
Missing features
In the future we will add actions for:
- Files
- Moderation
- Fine-tuning
Let us know if you’re interested!
Feedback
Feedback to our implementation of OpenAI is always very welcome. Reach out to us using the established channels or create an issue.