Update description

README.md

@@ -30,13 +30,14 @@ SlideDeck AI works in the following way:
 
 1. Given a topic description, it uses Mistral Nemo Instruct to generate the *initial* content of the slides. 
 The output is generated as structured JSON data based on a pre-defined schema.
-2. Subsequently, it uses the `python-pptx` library to generate the slides, 
+2. Next, it uses the keywords from the JSON output to search and download a few images with a certain probability.
+3. Subsequently, it uses the `python-pptx` library to generate the slides, 
 based on the JSON data from the previous step. 
 A user can choose from a set of three pre-defined presentation templates.
-3. At this stage onward, a user can provide additional instructions to *refine* the content.
+4. At this stage onward, a user can provide additional instructions to *refine* the content.
 For example, one can ask to add another slide or modify an existing slide.
 A history of instructions is maintained.
-4. Every time SlideDeck AI generates a PowerPoint presentation, a download button is provided.
+5. Every time SlideDeck AI generates a PowerPoint presentation, a download button is provided.
 Clicking on the button will download the file.
 
 
@@ -55,7 +56,8 @@ number of allowed characters in the textbox, pasting would not work.
 SlideDeck AI uses [Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) 
 via the Hugging Face Inference API.
 To run this project by yourself, you need to provide the `HUGGINGFACEHUB_API_TOKEN` API key,
-for example, in a `.env` file. Visit the respective websites to obtain the keys.
+for example, in a `.env` file. For image search, the `PEXEL_API_KEY` should be added. 
+Visit the respective websites to obtain the keys.
 
 
 # Live Demo

app.py

@@ -12,7 +12,6 @@ from langchain_community.chat_message_histories import (
 )
 from langchain_core.messages import HumanMessage
 from langchain_core.prompts import ChatPromptTemplate
-# from transformers import AutoTokenizer
 
 from global_config import GlobalConfig
 from helpers import llm_helper, pptx_helper, text_helper
@@ -123,8 +122,8 @@ def set_up_chat_ui():
     with st.expander('Usage Instructions'):
         st.markdown(GlobalConfig.CHAT_USAGE_INSTRUCTIONS)
         st.markdown(
-            'SlideDeck AI is powered by'
-            ' [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)'
+            'SlideDeck AI is powered by'  # noqa: E501
+            ' [Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407).'
         )
 
     # view_messages = st.expander('View the messages in the session state')

global_config.py

@@ -62,8 +62,10 @@ class GlobalConfig:
         ' You can also ask it to refine any particular slide, e.g.:\n'
         '- Make the slide with title \'Examples of AI\' a bit more descriptive.'
         '\n\n'
-        'See this [demo video](https://youtu.be/QvAKzNKtk9k) for a brief walkthrough.'
-        'SlideDeck AI does not have access to the Web.'
+        'See this [demo video](https://youtu.be/QvAKzNKtk9k) for a brief walkthrough.\n\n'
+        ' SlideDeck AI does not have access to the Web, apart for searching for images relevant'
+        ' to the slides. Photos are added probabilistically; transparency needs to be changed'
+        ' manually, if required.'
         '\n\n'
         'If you like SlideDeck AI, please consider leaving a heart ❤️ on the'
         ' [Hugging Face Space](https://huggingface.co/spaces/barunsaha/slide-deck-ai/) or'