Https support and updated Readme#5
Merged
google-oss-prow[bot] merged 7 commits intokubeflow:mainfrom Oct 6, 2025
Merged
Conversation
Signed-off-by: SanthoshToorpu <toorpusanthosh@gmail.com>
Signed-off-by: SanthoshToorpu <toorpusanthosh@gmail.com>
Signed-off-by: SanthoshToorpu <toorpusanthosh@gmail.com>
Signed-off-by: SanthoshToorpu <toorpusanthosh@gmail.com>
Contributor
franciscojavierarceo
left a comment
franciscojavierarceo
left a comment
There was a problem hiding this comment.
looks like we removed a lot of the pipeline code, was that on purpose?
Contributor
Author
|
Yeah @franciscojavierarceo its like a compiled version of the code. So the python file is equivalent to what we have rn....... |
Contributor
|
I don't see a compiled version of the code. I just see the files removed. |
Contributor
Author
|
Yeah the files that were removed are the compiled yaml from the python file so I thought why keep it. However if the yaml makes sense I'll add it back |
Contributor
|
we should keep all of it. |
Contributor
Author
|
Aight then I'll add em back |
Signed-off-by: SanthoshToorpu <toorpusanthosh@gmail.com>
Signed-off-by: SanthoshToorpu <toorpusanthosh@gmail.com>
Signed-off-by: SanthoshToorpu <toorpusanthosh@gmail.com>
franciscojavierarceo
approved these changes
Oct 6, 2025
Contributor
|
/lgtm |
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: franciscojavierarceo The full list of commands accepted by this bot can be found here. The pull request process is described here DetailsNeeds approval from an approver in each of these files:
Approvers can indicate their approval by writing |
zong0728
added a commit
to zong0728/docs-agent
that referenced
this pull request
Mar 22, 2026
Implements GSoC 2026 Agentic RAG spec Requirement kubeflow#5: 'Robust retry logic is a must for all tools. The agent implements exponential backoff with jitter for Vector DB retrievals and LLM API timeouts. If tools strictly fail, the agent is configured to transparently degrade, informing the user that Live code context is currently unreachable.' Changes: - shared/retry.py: reusable @with_retry decorator supporting both sync and async callables; uses AWS full-jitter strategy (random.uniform(0, delay)) to prevent thundering-herd on retry; exposes DEGRADED_RESULT sentinel string for LLM-visible outage messages - server/app.py, server-https/app.py: * milvus_search: remove silent exception swallow; add @with_retry (3 attempts, base 1s, max 10s, factor 2x + jitter); encoder loaded once at module level via _get_encoder() singleton * execute_tool: offload blocking milvus_search to asyncio.to_thread (websocket server) and run_in_threadpool (FastAPI server) so the async event loop stays responsive under concurrent load; on retry exhaustion return DEGRADED_RESULT so LLM communicates the outage to the user instead of silently hallucinating from empty context Signed-off-by: Shengzhong Guan <guan@cmu.edu> Made-with: Cursor
zong0728
added a commit
to zong0728/docs-agent
that referenced
this pull request
Mar 22, 2026
Implements GSoC 2026 Agentic RAG spec Requirement kubeflow#5: 'Robust retry logic is a must for all tools. The agent implements exponential backoff with jitter for Vector DB retrievals and LLM API timeouts. If tools strictly fail, the agent is configured to transparently degrade, informing the user that Live code context is currently unreachable.' Changes: - shared/retry.py: reusable @with_retry decorator supporting both sync and async callables; uses AWS full-jitter strategy (random.uniform(0, delay)) to prevent thundering-herd on retry; exposes DEGRADED_RESULT sentinel string for LLM-visible outage messages - server/app.py, server-https/app.py: * milvus_search: remove silent exception swallow; add @with_retry (3 attempts, base 1s, max 10s, factor 2x + jitter); encoder loaded once at module level via _get_encoder() singleton * execute_tool: offload blocking milvus_search to asyncio.to_thread (websocket server) and run_in_threadpool (FastAPI server) so the async event loop stays responsive under concurrent load; on retry exhaustion return DEGRADED_RESULT so LLM communicates the outage to the user instead of silently hallucinating from empty context Signed-off-by: Shengzhong Guan <guan@cmu.edu> Made-with: Cursor Signed-off-by: Shengzhong Guan <guan@cmu.edu>
8 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR features an updated readme and provision for usage with https as well as sockets