barunsaha commited on
Commit
e48ea08
1 Parent(s): 724babe

Update README and messages

Browse files
Files changed (2) hide show
  1. README.md +9 -6
  2. app.py +1 -3
README.md CHANGED
@@ -16,26 +16,29 @@ We spend a lot of time on creating the slides and organizing our thoughts for an
16
  With SlideDeck AI, co-create slide decks on any topic with Generative Artificial Intelligence.
17
  Describe your topic and let SlideDeck AI generate a PowerPoint slide deck for you—it's as simple as that!
18
 
 
 
19
 
20
  # Process
21
 
22
  SlideDeck AI works in the following way:
23
 
24
- 1. Given a topic description, it uses Llama 2 to generate the outline/contents of the slides.
25
  The output is generated as structured JSON data based on a pre-defined schema.
26
  2. Subsequently, it uses the `python-pptx` library to generate the slides,
27
  based on the JSON data from the previous step.
28
  Here, a user can choose from a set of three pre-defined presentation templates.
29
  3. In addition, it uses Metaphor to fetch Web pages related to the topic.
30
- 4. Finally, it uses Stable Diffusion 2 to generate an image, based on the title and each slide heading.
 
31
 
32
 
33
  # Local Development
34
 
35
- SlideDeck AI uses the Clarifai API of LangChain to interact with Llama 2.
36
- It also sends a Web request to Clarifai for the final step.
37
- To run this project by yourself, you need to provide the `CLARIFAI_PAT` and `METAPHOR_API_KEY` API keys,
38
- for example, in a `.env` file.
39
 
40
 
41
  # Live Demo
 
16
  With SlideDeck AI, co-create slide decks on any topic with Generative Artificial Intelligence.
17
  Describe your topic and let SlideDeck AI generate a PowerPoint slide deck for you—it's as simple as that!
18
 
19
+ SlideDeck AI is powered by [Mistral 7B Instruct](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1).
20
+ Originally, it was built using the Llama 2 API provided by Clarifai.
21
 
22
  # Process
23
 
24
  SlideDeck AI works in the following way:
25
 
26
+ 1. Given a topic description, it uses Mistral 7B Instruct to generate the outline/contents of the slides.
27
  The output is generated as structured JSON data based on a pre-defined schema.
28
  2. Subsequently, it uses the `python-pptx` library to generate the slides,
29
  based on the JSON data from the previous step.
30
  Here, a user can choose from a set of three pre-defined presentation templates.
31
  3. In addition, it uses Metaphor to fetch Web pages related to the topic.
32
+
33
+ 4. ~~Finally, it uses Stable Diffusion 2 to generate an image, based on the title and each slide heading.~~
34
 
35
 
36
  # Local Development
37
 
38
+ SlideDeck AI uses [Mistral 7B Instruct](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)
39
+ via the Hugging Face Inference API.
40
+ To run this project by yourself, you need to provide the `HUGGINGFACEHUB_API_TOKEN` and `METAPHOR_API_KEY` API keys,
41
+ for example, in a `.env` file. Visit the respective websites to obtain the keys.
42
 
43
 
44
  # Live Demo
app.py CHANGED
@@ -115,11 +115,9 @@ def build_ui():
115
 
116
  st.title(APP_TEXT['app_name'])
117
  st.subheader(APP_TEXT['caption'])
118
- st.markdown('Using [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1).')
119
  st.markdown('*If the JSON is generated or parsed incorrectly, try again later by making minor changes '
120
  'to the input text.*')
121
- st.markdown('~~*Running on GPT-4 at the moment. Image generation has been disabled. '
122
- 'Will run as long as the community plan supports* :)~~')
123
 
124
  with st.form('my_form'):
125
  # Topic input
 
115
 
116
  st.title(APP_TEXT['app_name'])
117
  st.subheader(APP_TEXT['caption'])
118
+ st.markdown('Powered by [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1).')
119
  st.markdown('*If the JSON is generated or parsed incorrectly, try again later by making minor changes '
120
  'to the input text.*')
 
 
121
 
122
  with st.form('my_form'):
123
  # Topic input