# Build and run the docker image
> docker compose up
# OR run natively in you have the rust toolchain installed.
> cp .env.template .env
> cargo run --release -p memex serve
# If everything is running correctly, you should see something like:
2023-06-13T05:04:21.518732Z  INFO memex: starting server with roles: [Api, Worker]

> curl http://localhost:8181/collections/test \
    -H "Content-Type: application/json" \
    --data @example_docs/state_of_the_union_2023.json
{
    "task_id": 1,
    "collection": "test",
    "status": "Queued",
    ...
}

> curl http://localhost:8181/tasks/1
{
    "task_id": 1,
    "status": "Processing"
}

> curl http://localhost:8181/collections/test/search \
    -H "Content-Type: application/json" \
    -X GET \
    -d "{\"query\": \"what does Biden say about taxes?\", \"limit\": 3}"
[{
    "id": <internal_document_id>,
    "segment": <document section>,
    "content": <content block>,
    "score": <relevancy score>
}, ...]

# In a different terminal, run memex
> cargo run --release -p memex serve
# In your main terminal
> cd examples/clippy
# NOTE: there is no duplicate detection so running this twice will add the file twice.
> cargo run -- load-file example_docs/state_of_the_union.txt
# To ask clippy about your files, use "ask"
> cargo run -- ask "what does biden say about taxes?"
# To ask clippy without referring to it's memex and _ONLY_ relying on the knowledge
# inside it's LLM, use "qq" / "quick-question"
> cargo run -- qq "wget command to save a file to a directory"
# To clear clippy's memory
> cargo run -- forget