Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
@@ -9,5 +9,52 @@ app_file: app.py
|
|
9 |
pinned: false
|
10 |
license: cc-by-4.0
|
11 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
|
13 |
-
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
9 |
pinned: false
|
10 |
license: cc-by-4.0
|
11 |
---
|
12 |
+
# Project Title: Diabetes Assistant
|
13 |
+
|
14 |
+
## Objective
|
15 |
+
The objective of this project was to showcase our individual learnings about large language models, translation application, chatbot, gradio and hugging face.
|
16 |
+
|
17 |
+
## Sources
|
18 |
+
- ChatGPT
|
19 |
+
- Copilot
|
20 |
+
- Hugging Face
|
21 |
+
- Gradio
|
22 |
+
- OpenAI Whisper (https://openai.com/research/whisper)
|
23 |
+
|
24 |
+
## Method
|
25 |
+
|
26 |
+
L3-AI Created an assistant to ask your diabetes questions and when needed translate responses to an alternate language.
|
27 |
+
|
28 |
+
1. <b>Transcription:</b> Individuals could either voice their questions by hitting the microphone, upload an mp3 of their question, or write their diabetes
|
29 |
+
related questions within the Hugging Face Application. For questions that were either voice activated or mp3 uploaded we used <i>openai/whisper-large</i> to
|
30 |
+
transcribe the audio into written format.
|
31 |
+
|
32 |
+
2. <b>LLM Model:</b> Using <i>WikipediaLoader</i>, we created a large language model that tapped into Wikipedia specifically grabbing information related to the diabetes
|
33 |
+
question.
|
34 |
+
|
35 |
+
3. <b>Chatbot Response and Voice Over:</b> L3-AI added a feature that allowed our Hugging Face Application to verbalize the response from the LLM as well as provide responses in
|
36 |
+
written format. We used <i>gTTS</i>, to provide written text to speech.
|
37 |
+
|
38 |
+
4. <b>Translation:</b> <i>Helsinki-NLP</i> was used to translate the information provided from the LLM.
|
39 |
+
|
40 |
+
5. <b>Gradio:</b> L3-AI used the gradio application to organize and produce each level and response of the four different models utilized.
|
41 |
+
|
42 |
+
6. <b>Hugging Face:</b> Finally, L3-AI pushed all information to Hugging Face Application for speed as well as production.
|
43 |
+
|
44 |
+
|
45 |
+
## Interface
|
46 |
+
|
47 |
+
https://huggingface.co/spaces/L3-AI/diabetes_assistant
|
48 |
+
|
49 |
+

|
50 |
+
|
51 |
+
## Learnings
|
52 |
+
Throughout this project we learned how to embed a chatbot function that called four different models and put into production our application in Hugging Face.
|
53 |
+
|
54 |
+
## Opportunities and Next Steps
|
55 |
+
For L3-AI concept design we centered on diabetes however, we thought in future endeavors expanding to other disease states would enhance the work that was started.
|
56 |
+
|
57 |
+
|
58 |
+
## Credits
|
59 |
+
We would like to thank our pets who kept us company as we worked on coding and this application.
|
60 |
|
|