Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add docai inference server capability #1520

Open
wants to merge 8 commits into
base: main
Choose a base branch
from
+4 −1
Open

Add docai inference server capability #1520

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
8c11f03
added support for passing model names to inference servers
ryanchesler Apr 1, 2024
57c9309
cleaned print statements
ryanchesler Apr 1, 2024
1b7c269
merge with main
ryanchesler Apr 1, 2024
ab0d9a0
Merge branch 'main' into docai_server
ryanchesler Apr 1, 2024
9e4c967
fixed docai inference issues
ryanchesler Apr 1, 2024
fd72413
fixed merge error
ryanchesler Apr 1, 2024
8a2933f
fixed merge error
ryanchesler Apr 1, 2024
a8432cb
fixed merge error
ryanchesler Apr 1, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions src/evaluate_params.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,6 +83,7 @@

'image_file',
'image_control',
'base_model'
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi, we use visible_models for this. Even though it sounds plural, for API it can just be single string.

]

# form evaluate defaults for submit_nochat_api
Expand Down
4 changes: 3 additions & 1 deletion src/gen.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4529,7 +4529,7 @@ def evaluate(
if not stream_output and img_file == 1:
from src.vision.utils_vision import get_llava_response
response, _ = get_llava_response(**llava_kwargs)

yield dict(response=response, sources=[], save_dict={}, error='', llm_answers={},
response_no_refs=response, sources_str='', prompt_raw='')
else:
Expand Down Expand Up @@ -4665,6 +4665,7 @@ def evaluate(

image_file=img_file,
image_control=None, # already stuffed into image_file
base_model=base_model,
)
assert len(set(list(client_kwargs.keys())).symmetric_difference(eval_func_param_names)) == 0
api_name = '/submit_nochat_api' # NOTE: like submit_nochat but stable API for string dict passing
Expand Down Expand Up @@ -5396,6 +5397,7 @@ def mean(a):""", ''] + params_list,
tts_speed,
image_file,
image_control,
None,
]
# adjust examples if non-chat mode
if not chat:
Expand Down
Loading