cheesyFishes
Joined 3 years ago
Karma
3
Submissions
9
Member since
Jun 6
Recent submissions
Comment · 1 year ago
Comment · 2 years ago
Pretty neat initial launch. What's top of mind to add to it?
Comment · 2 years ago
There is a PDF parser, LlamaParse, (which is open to everyone), and a managed ingestion/retrieval service, that is currently invite-only.
Planning broader releases in the future for sure.
Comment · 2 years ago
The output is either text or markdown, and from there you can handle it however you need.
In LlamaIndex for example, there are a a few markdown-specific classes that work well with this.
You can find an example over in the repo -- https://github.com/run-llama/llama_parse/blob/main/examples/...
Comment · 2 years ago
This is actually what llama-index does if you don't use a vectordb integration
Comment · 3 years ago
The real advantage of LLMs is not search -- that's just something that's easy to show people. No one really wants to talk to an LLM instead of using Google search.
The real value is being general reasoning machines. Being able to accomplish basic tasks, retrieve information, etc. is the key value.
Seems like CLI tools are all the rage these days