FEATURE: Add Multi Modal Capabilities to Flowise #1419
Conversation
# Conflicts: # packages/server/src/index.ts
…lder on the server side when saving messages.
…nd can run inference
# Conflicts: # packages/server/src/index.ts # packages/ui/src/views/chatmessage/ChatMessage.js
# Conflicts: # packages/server/src/index.ts
# Conflicts: # packages/server/src/database/migrations/mysql/index.ts # packages/server/src/database/migrations/postgres/index.ts # packages/server/src/database/migrations/sqlite/index.ts
# Conflicts: # packages/server/src/index.ts
packages/components/nodes/multimodal/OpenAI/OpenAIVisionChain.ts
Outdated
Show resolved
Hide resolved
|
Update after touchup:
|
# Conflicts: # packages/components/nodes/agents/MRKLAgentChat/MRKLAgentChat.ts
|
related chat embedded PR |
|
@HenryHengZJ @chungyau97 Issues have all been fixed. We can review and merge this. I think everything's good to go on @vinodkiran's end too. |
|
@0xi4o, thanks for the fix for invalid characters in file |
|
Another error where importing flows then turn on Steps to reproduce error:
|
|
Another issue: 1.) Open OpenAI Whisper, put in credential: 2.) switch to assembly ai, you can see the openai credential there: I think that's because of the |
solved |
solved |
| </div> | ||
| {inputParam.type === 'credential' && ( | ||
| <CredentialInputHandler | ||
| key={speechToText[selectedProvider]?.credentialId} |
There was a problem hiding this comment.
@0xi4o this is where you can specify a key so that a new element is rendered, hence you dont need to put credentialNames in the useEffect
| } | ||
| }) | ||
|
|
||
| this.app.get('/api/v1/get-upload-path', async (req: Request, res: Response) => { |
There was a problem hiding this comment.
Reminder to backport this route to the new way modularity express router PR - #1806
|
Could there be an option to configure another audio or image model (selfhosted)? |
|
Awesome feature. It would be great to add it to the chat embed as well. |
No description provided.