* feat(block): Add AIImageGeneratorBlock
This commit adds the AIImageGeneratorBlock class to the backend. The AIImageGeneratorBlock is responsible for generating images using various AI models through a unified interface.
* Remove unsupported inputs and add more styles
* Update autogpt_platform/backend/backend/blocks/ai_image_generator_block.py
Co-authored-by: Reinier van der Leer <pwuts@agpt.co>
* run format
* Add test mock
* mock client run
* Refactor AIImageGeneratorBlock to use a separate function for running the client
* Update Credential description
* Rename ModelProvider to ImageGenModel
* Add missing block run function
* fix mock
* .
* Refactor AIImageGeneratorBlock to move run_client function inside class
* Fix broken reference to run client and tidy code.
* Refactor AIImageGeneratorBlock to improve code structure and error handling
* Move client into run client instantiation function.
* Refactor AIImageGeneratorBlock to handle output as FileOutput and improve error handling
* run format
---------
Co-authored-by: Reinier van der Leer <pwuts@agpt.co>
* Add support for default credentials to unreal block
* Refactor block cost configuration and add new blocks
This commit refactors the block cost configuration file and adds support for new blocks. The changes include:
- Importing the `AIMusicGeneratorBlock`, `JinaEmbeddingBlock`, and `UnrealTextToSpeechBlock` classes
- Updating the `BLOCK_COSTS` dictionary to include costs for the new blocks
These changes enable the usage of the newly introduced blocks.
- Resolves#8635
- fix(frontend): Fix type mismatch of `CredentialsField` schema between frontend and backend
- Fix usages of `credentialsSchema.credentials_provider`
- refactor(backend): Create `CredentialsFieldSchemaExtra` model in backend so it can be mirrored directly in frontend
- Add check to enforce multi-provider `CredentialsField` always has `discriminator`
- dx: Add type checking shortcut `yarn type-check` / `npm run type-check` for frontend
- Change `provider` of default credentials to actual provider names (e.g. `anthropic`), remove `llm` provider
- Add `discriminator` and `discriminator_mapping` to `CredentialsField` that allows to filter credentials input to only allow providers for matching models in `useCredentials` hook (thanks @ntindle for the idea!); e.g. user chooses `GPT4_TURBO` so then only OpenAI credentials are allowed
- Choose credentials automatically and hide credentials input on the node completely if there's only one possible option
- Move `getValue` and `parseKeys` to utils
- Add `ANTHROPIC`, `GROQ` and `OLLAMA` to providers in frontend `types.ts`
- Add `hidden` field to credentials that is used for default system keys to hide them in user profile
- Now `provider` field in `CredentialsField` can accept multiple providers as a list
-----------------
Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co>
Co-authored-by: Reinier van der Leer <pwuts@agpt.co>
* feat(platform): Add AIMusicGeneratorBlock for music generation
* refactor(platform): Refactor AIMusicGeneratorBlock for improved error handling and logging
* refactor(ui): Refactor ContentRenderer to support audio rendering
* format
* Frontend format and lint
* add pinecone and jina blocks
* udpate based on comments
* backend updates
* frontend updates
* type hint
* more type hints
* another type hint
* update run signature
* shared jina provider
* fix linting
* lockfile
* remove noqa
* remove noqa
* remove vector db folder
* line
* update pincone credentials provider
* fix imports
* formating
* update frontend
* Test (#8425)
* h
* Discard changes to autogpt_platform/backend/poetry.lock
* fix: broken dep
---------
Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co>
* fix(backend): Fix error pin output not being propagated into the next nodes
* fix(backend): Reverse pyro config refactor
* Revert "fix(backend): Fix error pin output not being propagated into the next nodes"
This reverts commit 2ff50a94ec.
---------
Co-authored-by: Aarushi <50577581+aarushik93@users.noreply.github.com>
