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

community: Voice Input Support For Ollama Models #28428

Closed

Conversation

faizannaseerr
Copy link

@faizannaseerr faizannaseerr commented Nov 30, 2024

Tool to provide voice input support for Ollama models.

Description: Added voice input tool for Ollama model that holds two classes that extend BaseBlobParser & BaseTool respectively, to allow for voice input (pre-saved or on the spot) on various Ollama model chains, as the user requires. Details on how to utilize the tool (e.g. use cases) can be found in the docs/integrations/tools folder in 'ollama_voice_input.ipynb'.

Issue: #27717

Dependencies: 'sounddevice', 'scipy' for voice recording (not anymore as per my knowledge, except for note below)

Twitter Handle: @faizannaseerr

Lint & Test: I ran lint & tests locally, and everything seemed fine as per my knowledge.

Added Test & Docs: Unit tests for modules and docs on how to use the tool have been added.

Additional Notes:

  • There is a unit test for long audio input that should use an audio file named 'long_audio.wav' in the langchain_community/tests/examples file. I have not added this file yet as I could not find any long, free-to-use, audio input file online and therefore can leave this unit test out if required, or can use it if a long audio input file is found (that leads to several Document objects after the parse)
  • Will fix imports shortly if required (still some being re-imported from LangChain, not sure if they need to be altered or not)

Copy link

vercel bot commented Nov 30, 2024

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name Status Preview Comments Updated (UTC)
langchain ✅ Ready (Inspect) Visit Preview 💬 Add feedback Dec 6, 2024 2:56am

@dosubot dosubot bot added the size:L This PR changes 100-499 lines, ignoring generated files. label Nov 30, 2024
@faizannaseerr faizannaseerr changed the title community: Voice Input Support For Ollama Models #27717 community: Voice Input Support For Ollama Models Nov 30, 2024
@dosubot dosubot bot added community Related to langchain-community 🤖:docs Changes to documentation and examples, like .md, .rst, .ipynb files. Changes to the docs/ folder labels Nov 30, 2024
@dosubot dosubot bot added size:XL This PR changes 500-999 lines, ignoring generated files. and removed size:L This PR changes 100-499 lines, ignoring generated files. labels Dec 1, 2024
@efriis
Copy link
Member

efriis commented Dec 10, 2024

going to close because the ci issues stem from dependencies we don't want to package here. The description alludes to this , and if you want to re-contribute, would recommend reading our docs on optional dependencies, as well as some of the Whisper parsers in community (instead of a tool implemented here)

@efriis efriis closed this Dec 10, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
community Related to langchain-community 🤖:docs Changes to documentation and examples, like .md, .rst, .ipynb files. Changes to the docs/ folder size:XL This PR changes 500-999 lines, ignoring generated files.
Projects
Status: Closed
Development

Successfully merging this pull request may close these issues.

2 participants