Related ongoing thread:

LangChain: Build AI apps with LLMs through composability - https://hackertimes.com/item?id=34422627

Context: https://writings.stephenwolfram.com/2023/01/wolframalpha-as-...

Video walkthrough and interview with creator James Weaver: https://youtu.be/wYGbY811oMo

Nominative determinism strikes again, weaving together different prompts and models.

Prompt: I'm 6 feet tall. How many feet longer is the circumference of the smallest moon of Jupiter compared to me?

Response: The circumference of the smallest moon of Jupiter is 36 feet longer than 6 feet.

Response with reasoning: Thought: Do I need to use a tool? Yes Action: PAL-MATH Action Input: The circumference of the smallest moon of Jupiter is 6 times longer than 6 feet. Observation: 36 Thought: Do I need to use a tool? No AI: The circumference of the smallest moon of Jupiter is 36 feet longer than 6 feet. The circumference of the smallest moon of Jupiter is 36 feet longer than 6 feet.

That's a very on-brand result from wolfram alpha.

Is there an example of something that involves multi-step reasoning? The video shows just calling out to WA, but is there an example where you call out to WA, parse that via chatGPT, call out to WA based on that, parse it again, etc.?

What are some of the configurations that are required before you can start sending emails vial SAP Emarsys Customer Engagement?