feat (example): Add Ollama Retrieval Example

[hcmlinj]

Background

Providing specific information or domain knowledge ensures that the AI gives priority to this when responding. The main questions we will ask are "What is this?" If there is direct relevance, prioritize answering based on the information we provided. Otherwise, simply respond without referencing our information, and avoid mentioning the provided details unless necessary. When asking the AI a question, we expect foo and f4 to be answered based on the information we provided. When asking about foodpanda and panda, we expect the AI to respond based on its own knowledge.

Testing

This is an example executed on my laptop.

#2 foo
9527

#1 foodpanda
Foodpanda is an online food delivery service platform. It allows users to order food from various restaurants in their area and have it delivered to their doorstep.

#3 f4
F4 refers to a Taiwanese boy band that was formed in 2001 after the success of the Taiwanese drama Meteor Garden, where they starred.

#4 panda
Panda is a type of bear native to China. It is known for its black and white fur. The term "panda" is not directly related to the provided context about Foo or F4.

PR Checklist

• [x] Read the Contributing documentation.
• [x] Read the Code of conduct documentation.
• [x] Name your Pull Request title clearly, concisely, and prefixed with the name of the primarily affected package you changed according to Good commit messages (such as memory: add interfaces for X, Y or util: add whizzbang helpers).
• [x] Check that there isn't already a PR that solves the problem the same way to avoid creating a duplicate.
• [ ] Provide a description in this PR that addresses what the PR is solving, or reference the issue that it solves (e.g. Fixes #123).
• [x] Describes the source of new concepts.
• [x] References existing implementations as appropriate.
• [ ] Contains test coverage for new functions.
• [x] Passes all golangci-lint checks.