max token ruduced

max token increased

data included in prompt

full summary generation

only one section working

model loading optimization

preload

summary

patient summary working

summary fixes

section wise summary generation

`Refactored codebase with various changes and deletions across multiple files`

prompt change

update model loader token limit

token limit increased

token limit increased and ensure required fields

chunking fix

chunking

summary markdown

summary to mardown removed

old summary tracking removed so that will generate a fresh new summary everytime

max new tokens

old summary logic changed

documentation and max new token update

summary length cutting off

summary consistancy

docker gguf thread count change

Merge branch 'FT-DEV-27/08/2025'

model loader time out fixing

model loader time out

Merge branch 'FT-DEV-27/08/2025'

model loader gguf fixes

Merge branch 'FT-DEV-27/08/2025'

gguf fix

Merge branch 'FT-DEV-27/08/2025'

duplicate llamacpp requirement

model manager

optimization

optimized code

gguf fix

model loader gguf

revert

dockerfile updates

pycache

optimized memory runtime loading of model

gguf optimized

gguf model

openvino model change

Add OpenVINO model using Git LFS

docker build