sagemaker streaming

[dartpain]

• What kind of change does this PR introduce? (Bug fix, feature, docs update, ...)
  Adds proper sagemaker endpoint handling with respone streaming
• Why was this change needed? (You can also link to an open issue here)
  It allows to stream responses now
• Other information:

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
docs-gpt	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Oct 6, 2023 0:23am
nextra-docsgpt	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Oct 6, 2023 0:23am

[codecov]

Codecov Report

Merging #449 (4f5e363) into main (aa9a024) will increase coverage by 0.06%.
Report is 22 commits behind head on main.
The diff coverage is 17.85%.

❗ Current head 4f5e363 differs from pull request most recent head 4957285. Consider uploading reports for the commit 4957285 to get more accurate results

@@            Coverage Diff             @@
##             main     #449      +/-   ##
==========================================
+ Coverage   15.97%   16.03%   +0.06%     
==========================================
  Files          59       59              
  Lines        2673     2725      +52     
==========================================
+ Hits          427      437      +10     
- Misses       2246     2288      +42     

Files	Coverage Δ
application/core/settings.py	100.00% <100.00%> (ø)
application/llm/sagemaker.py	22.22% <11.53%> (-31.12%)	⬇️

📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more