Skip to content

Python: Clarify Redis context retrieval scope #8584

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
Eduard van Valkenburg (eavanvalkenburg) merged 2 commits into from
Sep 21, 2026
Merged

Python: Clarify Redis context retrieval scope #8584

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
568b998
Python: Clarify Redis context retrieval scope
eavanvalkenburg Sep 21, 2026
8d39b90
Python: Document required Redis context scope
eavanvalkenburg Sep 21, 2026
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
15 changes: 11 additions & 4 deletions python/packages/redis/agent_framework_redis/_context_provider.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,11 @@ class RedisContextProvider(ContextProvider):
"""Redis context provider using the new ContextProvider hooks pattern.

Stores context in Redis and retrieves scoped context via full-text or
optional hybrid vector search.
optional hybrid vector search. Retrieval spans sessions and is filtered by
every non-empty ``application_id``, ``agent_id``, and ``user_id``. At least
one identifier must be non-empty. Omitted identifiers do not constrain
retrieval, so applications should provide each stable, trusted identifier
that represents an intended isolation boundary.
"""

DEFAULT_CONTEXT_PROMPT = "## Memories\nConsider the following memories when answering user questions:"
Expand Down Expand Up @@ -81,9 +85,12 @@ def __init__(
vector_field_name: The name of the vector field in Redis.
vector_algorithm: The algorithm to use for vector search.
vector_distance_metric: The distance metric to use for vector search.
application_id: The application ID to scope the context.
agent_id: The agent ID to scope the context.
user_id: The user ID to scope the context.
application_id: Optional application-level retrieval scope. When
omitted, retrieval is not filtered by application.
agent_id: Optional agent-level retrieval scope. When omitted,
retrieval is not filtered by agent.
user_id: Optional user-level retrieval scope. When omitted,
retrieval is not filtered by user.
context_prompt: The context prompt to use for the provider.
redis_index: The Redis index to use for the provider.
overwrite_index: Whether to overwrite the existing Redis index.
Expand Down
Loading