Skip to content
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.

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

Add skeletal metadata for Upstage AI: no implementation due to spec ambiguity #1072

Merged
merged 1 commit into from
May 8, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@ public final class ProviderConstants {
public static final String VERTEXAI = "vertexai";
public static final String COHERE = "cohere";
public static final String NVIDIA = "nvidia";
public static final String UPSTAGE_AI = "upstageAI";
public static final String VOYAGE_AI = "voyageAI";
public static final String CUSTOM = "custom";
public static final String MISTRAL = "mistral";
Expand Down
34 changes: 30 additions & 4 deletions src/main/resources/embedding-providers-config.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -287,8 +287,34 @@ stargate:
models:
- name: mistral-embed
vector-dimension: 1024
# upstage:
# see https://developers.upstage.ai/docs/apis/embeddings
# NOTE: they have a model for storing and a diff one for reading, this is different to everyone else
# holding on the config / implementation until we confirm if this can change

# NOTE: UpstageAI have a model for storing and a diff one for reading: this is different
# from everyone else.
# Holding on the config / implementation until we confirm if this can change
# NOTE: no free tier available, CC required
upstageAI:
# see https://developers.upstage.ai/docs/apis/embeddings
# NOT enabled until
enabled: false
url: https://api.upstage.ai/v1/solar/embeddings
supported-authentications:
NONE:
enabled: false
HEADER:
enabled: true
tokens:
- accepted: x-embedding-api-key
forwarded: Authorization
SHARED_SECRET:
enabled: false
tokens:
- accepted: providerKey
forwarded: Authorization
parameters:
properties:
models: # NOTE: this is where weirdness exists; including model names as example
- name: solar-1-mini-embedding-query
vector-dimension: 4096
- name: solar-1-mini-embedding-passage
vector-dimension: 4096