Skip to content

Personalized news chatbot with adaptive learning and session management for a consistent and personalized user experience.

License

Notifications You must be signed in to change notification settings

anilaltuner/personalized-news-agent

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Personalized News Chatbot

This repository builded top of the Personalized Feed repository. Frontend developed with Streamlit, Recommendation engine developed with Firstbatch.

Features

  • Adaptive Conversations: Our chatbot learns from your previous interactions and tailors the conversation accordingly.
  • News Content Integration: Engage with news content that you prefer. Like the content you want and the chatbot adapts!
  • Modern Interface: Dark-themed, sleek design ensures an enjoyable user experience.

How It Works

Personalization Levels:

Level 1: The chatbot starts without prior knowledge. Conversations are general and exploratory.

Level 2: As you interact, the chatbot aligns its responses closely with your expressed preferences.

Level 3: With further interactions, the chatbot leverages both your explicit signals and contextually linked topics to diversify the conversation.

Level 4: The chatbot takes brave leaps, introducing topics and directions that are related to your interests but offer fresh perspectives.

Note: The chatbot is predominantly influenced by the last three significant interactions to ensure that the conversation remains dynamic and relevant.

FirstBatch Algorithm in Detail

FirstBatch SDK Documentation

Setup

  1. Clone the repository:

    git clone git@github.com:anilaltuner/personalized-news-agent.git
  2. Install the required libraries:

    pip install -r requirements.txt
  3. Set up your API keys in the st.secrets configuration. Ensure you have API keys for both FirstBatch and Pinecone. A secrets.toml example:

    "custom_algo_id" = "[algo_id]"
    "pinecone_index"="[pinecone_index_name]"
    "firstbatch_db_name"="[firstbatch_db]"
    "embedding_size"="[embbedding_size_of_vectors]"
    
    [api]
    "pinecone_api_key"="[pinecone_key]"
    "pinecone_env"="[pinecone_env]"
    "firstbatch_api_key"="[firstbatch_key]"
    
  4. Run the Streamlit app:

    streamlit run app.py

Feedback & Contributions

We value your feedback and contributions. If you find a bug or have a feature request, please open an issue. Pull requests are also welcome!

About

Personalized news chatbot with adaptive learning and session management for a consistent and personalized user experience.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages