Skip to content

Fix too large payload error on function apps by reducing rate of processing #162

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

Merged
merged 4 commits into from
Feb 9, 2025
Merged

Fix too large payload error on function apps by reducing rate of processing #162

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
d6c4741
Update
BenConstable9 Feb 9, 2025
c442539
Reduce batch size
BenConstable9 Feb 9, 2025
67971b2
Update params
BenConstable9 Feb 9, 2025
49492b1
Reduce batch
BenConstable9 Feb 9, 2025
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
10 changes: 5 additions & 5 deletions deploy_ai_search_indexes/src/deploy_ai_search_indexes/ai_search.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -212,7 +212,7 @@ def get_mark_up_cleaner_skill(self, chunk_by_page: False) -> WebApiSkill:
batch_size = 2
degree_of_parallelism = 2
else:
batch_size = 16
batch_size = 4
degree_of_parallelism = 16

if chunk_by_page:
Expand Down Expand Up @@ -273,10 +273,10 @@ def get_mark_up_cleaner_skill(self, chunk_by_page: False) -> WebApiSkill:

def get_semantic_chunker_skill(
self,
num_surrounding_sentences: int = 1,
num_surrounding_sentences: int = 2,
similarity_threshold: float = 0.8,
max_chunk_tokens: int = 200,
min_chunk_tokens: int = 50,
max_chunk_tokens: int = 500,
min_chunk_tokens: int = 150,
) -> SplitSkill:
"""Get the skill for text split.

Expand All @@ -296,7 +296,7 @@ def get_semantic_chunker_skill(
batch_size = 2
degree_of_parallelism = 2
else:
batch_size = 16
batch_size = 8
degree_of_parallelism = 16

semantic_text_chunker_skill_inputs = [
Expand Down
4 changes: 2 additions & 2 deletions deploy_ai_search_indexes/src/deploy_ai_search_indexes/image_processing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -301,10 +301,10 @@ def get_indexer(self) -> SearchIndexer:
# Only place on schedule if it is not a test deployment
if self.test:
schedule = None
batch_size = 4
batch_size = 1
else:
schedule = {"interval": "PT15M"}
batch_size = 16
batch_size = 2

if self.environment.use_private_endpoint:
execution_environment = IndexerExecutionEnvironment.PRIVATE
Expand Down
6 changes: 3 additions & 3 deletions image_processing/src/image_processing/semantic_text_chunker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,10 +12,10 @@
class SemanticTextChunker:
def __init__(
self,
num_surrounding_sentences: int = 1,
num_surrounding_sentences: int = 2,
similarity_threshold: float = 0.8,
max_chunk_tokens: int = 200,
min_chunk_tokens: int = 50,
max_chunk_tokens: int = 500,
min_chunk_tokens: int = 150,
):
self.num_surrounding_sentences = num_surrounding_sentences
self.similarity_threshold = similarity_threshold
Expand Down
Loading