generated from amazon-archives/__template_Apache-2.0
-
Notifications
You must be signed in to change notification settings - Fork 421
Closed
Labels
enhancementNew feature or requestNew feature or requestready for contributionPull requests welcomePull requests welcome
Description
Problem Statement
Strands agents currently reads messages in sequence from the session management datastore, which can lead to longer reads for long conversations.
Ref:
sdk-python/src/strands/session/s3_session_manager.py
Lines 288 to 289 in 4b29edc
for key in message_keys: message_data = self._read_s3_object(key) sdk-python/src/strands/session/file_session_manager.py
Lines 236 to 238 in 4b29edc
for filename in message_files: file_path = os.path.join(messages_dir, filename) message_data = self._read_file(file_path)
Proposed Solution
Implement a concurrent read of messages to help speed up the retrieval of messages from session datastore
Use async
, do not use threads.
Use Case
Anyone using a session manager can speed up their retrieval of messages by concurrently reading the messages.
Alternatives Solutions
No response
Additional Context
No response
Metadata
Metadata
Assignees
Labels
enhancementNew feature or requestNew feature or requestready for contributionPull requests welcomePull requests welcome