#+title: Requests

#+begin_src bash
curl -X 'GET' \
  'http://localhost:8080/clear/' \
  -H 'accept: application/json'
#+end_src

#+RESULTS:
: OK

#+begin_src bash
# curl command to localhost and post the message "hi there"
curl -X 'POST' \
  'http://localhost:8080/submit/' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
  "author": "ben",
  "content": "SAN FRANCISCO, May 2, 2023 PRNewswire -- GitLab Inc., the most comprehensive, scalable enterprise DevSecOps platform for software innovation, and Google Cloud today announced an extension of its strategic partnership to deliver secure AI offerings to the enterprise. GitLab is trusted by more than 50% of the Fortune 100 to secure and protect their most valuable assets, and leads with a privacy-first approach to AI. By leveraging Google Cloud'\''s customizable foundation models and open generative AI infrastructure, GitLab will provide customers with AI-assisted features directly within the enterprise DevSecOps platform."
}'
#+end_src

#+RESULTS:
: Submitted job 6012b198ffe0467d9344a196a2ced121

#+begin_src bash
curl -X 'POST' \
  'http://localhost:8080/submit/' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
  "author": "ben",
  "content": "In literature discussing why ChatGPT is able to capture so much of our imagination, I often come across two narratives: Scale: throwing more data and compute at it. UX: moving from a prompt interface to a more natural chat interface. A narrative that is often glossed over in the demo frenzy is the incredible technical creativity that went into making models like ChatGPT work. One such cool idea is RLHF (Reinforcement Learning from Human Feedback): incorporating reinforcement learning and human feedback into NLP. RL has been notoriously difficult to work with, and therefore, mostly confined to gaming and simulated environments like Atari or MuJoCo. Just five years ago, both RL and NLP were progressing pretty much orthogonally – different stacks, different techniques, and different experimentation setups. It’s impressive to see it work in a new domain at a massive scale. So, how exactly does RLHF work? Why does it work? This post will discuss the answers to those questions."
}'
#+end_src

#+RESULTS:
: Submitted job 05058b906f524fb4bfedc4f5a84eff06

#+begin_src bash
curl -X 'GET' \
  'http://localhost:8080/check_status/6012b198ffe0467d9344a196a2ced121' \
  -H 'accept: application/json'
#+end_src

#+RESULTS:
| {"id":"6012b198ffe0467d9344a196a2ced121" | status:"done" | last_updated:"2023-05-08T12:27:07"} |

#+begin_src bash
curl -X 'GET' \
  'http://localhost:8080/recent/' \
  -H 'accept: application/json'
#+end_src

#+RESULTS:
| [{"id":"05058b906f524fb4bfedc4f5a84eff06" | author:"ben" | summary:"A new approach to NLP that incorporates reinforcement learning and human feedback. How does it work? Why does it work? In this post | I’ll explain how it works. RLHF is a new approach to NLP that incorporates reinforcement learning and human feedback. It’s a new approach to NLP that incorporates reinforcement learning and human feedback. It’s a new approach to NLP that incorporates reinforcement learning and human feedback. It’s a new approach to NLP that incorporates reinforcement learning and human feedback. It’s a new approach to NLP that incorporates reinforcement learning and human feedback." | tags:["#general" | #rlhf] | date:"2023-05-08T12:27:31"} | {"id":"6012b198ffe0467d9344a196a2ced121" | author:"ben" | summary:"GitLab | the most comprehensive | scalable enterprise DevSecOps platform for software innovation | and Google Cloud today announced an extension of their strategic partnership to deliver secure AI offerings to the enterprise. By leveraging Google Cloud's customizable foundation models and open generative AI infrastructure | GitLab will provide customers with AI-assisted features directly within the enterprise DevSecOps platform. The company's AI capabilities are designed to help enterprises improve productivity and reduce costs." | tags:["#general"] | date:"2023-05-08T12:27:07"}] |