I recently experimented with OpenAI's API using LangChain. The possibilities of what we can achieve with this technology are truly endless! In this thread, I'll share how I used LangChain to build an app that generates responses to questions based on YouTube video content.
@PLANTandB It works with the free version as well but there is a catch. For long documents you will be calling the API repeatedly with each chunk of texts. The free version has a limit on number of API calls per minute.
@khairulhaaziqq For question answering, I passed each split along with the full summary to get an answer from each part. LangChain's map-rerank method will choose the best answer
@TheZombieth@hwchase17 For longer videos (more than 4000 tokens), I split up the document with enough overlap to ensure continuity, sent the smaller parts to the LLM, got the summary for each part, and finally combined the summaries to get the final result. Langchain's MapReduce method lets you do that
The best part? Getting started was easy. LangChain provides access to different LLMs, allowing me to incorporate external knowledge sources and chain them with ease.
@hwchase17 - thanks for making it this easy!
Next, I used LangChain's map-rerank method to get the final answer. By tuning the prompts, I was able to generate responses limited to the video's context. #AI#NLP#MachineLearning#ChatGPT
Recently, there's been a lot of buzz surrounding Microsoft's integration of ChatGPT with Bing and its potential to challenge Google Search.
However, it's important to understand the bigger picture.
#microsoft#chatgpt3#google#bing#innovation#paradigmshift#ai#bard
I believe the integration of ChatGPT with Bing and Bard with Google Search could lead to a paradigm shift in the way we seek information, and the competition it sparks could drive further innovation in the field.