support multiple nodes of a graph, apply different endpoint env for different node #176
Conversation
This file contains 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
Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: Dolpher Du <[email protected]> Signed-off-by: KfreeZ <[email protected]>
- Generate the component manifests into a single flat direcotry 'common' - Add a special version manifest for docsum-llm-uservice Signed-off-by: Lianhao Lu <[email protected]> Signed-off-by: KfreeZ <[email protected]>
- Remove unused probes - Support conditionally disable probes per GMC request Signed-off-by: Lianhao Lu <[email protected]> Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: Lianhao Lu <[email protected]> Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: Lianhao Lu <[email protected]> Signed-off-by: KfreeZ <[email protected]>
This is to prevent pre-commit lint the whitespace at the end of line. Signed-off-by: Lianhao Lu <[email protected]> Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: Lianhao Lu <[email protected]> Signed-off-by: KfreeZ <[email protected]>
- Added helm test for chart redis-vector-db - Update the chart README Signed-off-by: Lianhao Lu <[email protected]> Signed-off-by: KfreeZ <[email protected]>
- Added helm test for chart tgi - Update the chart README Signed-off-by: Lianhao Lu <[email protected]> Signed-off-by: KfreeZ <[email protected]>
- Added helm test for chart tei - Update the chart README Signed-off-by: Lianhao Lu <[email protected]> Signed-off-by: KfreeZ <[email protected]>
- Added helm test for chart teirerank - Update the chart README Signed-off-by: Lianhao Lu <[email protected]> Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: Lianhao Lu <[email protected]> Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: KfreeZ <[email protected]>
irisdingbj
reviewed
Jul 17, 2024
| @@ -23,6 +23,7 @@ spec: | |||
| serviceName: embedding-svc | |||
| config: | |||
| endpoint: /v1/embeddings | |||
| TEI_EMBEDDING_ENDPOINT: TeiEmbedding | |||
There was a problem hiding this comment.
This should use servcieName, in this case tei-embedding-svc.
irisdingbj
reviewed
Jul 17, 2024
| @@ -33,6 +34,7 @@ spec: | |||
| serviceName: retriever-svc | |||
| config: | |||
| endpoint: /v1/retrieval | |||
| REDIS_URL: VectorDB | |||
There was a problem hiding this comment.
same here, use redis-vector-db, in this way we can support multiple endpoint for switch scenario
irisdingbj
reviewed
Jul 17, 2024
| @@ -43,6 +45,7 @@ spec: | |||
| serviceName: reranking-svc | |||
| config: | |||
| endpoint: /v1/reranking | |||
| TEI_RERANKING_ENDPOINT: TeiReranking | |||
irisdingbj
reviewed
Jul 17, 2024
| @@ -55,6 +58,7 @@ spec: | |||
| serviceName: llm-svc | |||
| config: | |||
| endpoint: /v1/chat/completions | |||
| TGI_LLM_ENDPOINT: Tgi | |||
Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: KfreeZ <[email protected]>
Signed-off-by: KfreeZ <[email protected]>
|
use #203 to commit code |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Description
#166
this PR also adopt the new manifest, when new manifest is merged, some unnecessary code will be removed for simplicity
mark it as draft
Issues
List the issue or RFC link this PR is working on. If there is no such link, please mark it as
n/a.Type of change
List the type of change like below. Please delete options that are not relevant.
Dependencies
List the newly introduced 3rd party dependency if exists.
Tests
Describe the tests that you ran to verify your changes.