With the original prompt, the chain keeps trying to jump straight to
doing math directly, without first looking up ages. With this two-part
question, it behaves more as intended:
> Entering new ZeroShotAgent chain...
How old is Olivia Wilde's boyfriend? What is that number raised to the
0.23 power?
Thought: I need to find out how old Olivia Wilde's boyfriend is, and
then use a calculator to calculate the power.
Action: Search
Action Input: Olivia Wilde's boyfriend age
Observation: While Wilde, 37, and Styles, 27, have both kept a low
profile when it comes to talking about their relationship, Wilde did
address their ...
Thought: Olivia Wilde's boyfriend is 27 years old.
Action: Calculator
Action Input: 27^0.23
> Entering new LLMMathChain chain...
27^0.23
```python
import math
print(math.pow(27, 0.23))
```
Answer: 2.1340945944237553
> Finished LLMMathChain chain.
Observation: Answer: 2.1340945944237553
Thought: I now know the final answer.
Final Answer: 2.1340945944237553
> Finished ZeroShotAgent chain.
Add MemoryChain and ConversationChain as chains that take a docstore in
addition to the prompt, and use the docstore to stuff context into the
prompt. This can be used to have an ongoing conversation with a chatbot.
Probably needs a bit of refactoring for code quality
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Also updated docs, and noticed an issue with the add_texts method on
VectorStores that I had missed before -- the metadatas arg should be
required to match the classmethod which initializes the VectorStores
(the add_example methods break otherwise in the ExampleSelectors)
Without the print on the `llm` call, the new user sees no visible effect
when just getting started. The assumption here is the new user is
running this in a new sandbox script file or repl via copy-paste.