Extend endpointOai.ts to allow usage of extra sampling parameters (#1032)

feat: add support for anthropic on vertex (#958)

Add temperature to Llama 3 70B on HuggingChat (#1119)

Fix context of logger (#1112)

fix(chart): remove useless param (#1110)

Ensures more consistent hyperparameters to Phi-3-mini-4k-instruct (#1095)

Fix OpenAI Embeddings Auth Issue (#1077)

fix(chart): adjust resources (#1109)

Update scripts & documentations to reflect new prod setup (#1107)

Bump version to 0.8.4 (#1108)

[VertexAI] Add support for tools parameter (#1065)

fix(chart): add ADDRESS_HEADER and XFF_DEPTH for IP rate limiting (#1105)

fix(github): use sha as image version (#1103)

fix(github): docker deploy version (#1102)

fix(chart): update service metrics port name (#1101)

Clean up internal image action (#1100)

Use correct internal registry (#1099)

Kubernetes infra (#1088)

Move vars to dynamic, add metrics (#1085)

retry text area height (#1091)

Add truncate to task model (#1090)

Add the simplest healthcheck route (#1089)

Use pino for logs (#1086)

Sort by Trending to default (#1082)

Adds <s> to Phi-3-mini-4k-instruct template configuration (#1081)

Reduce new tokens on command R+ (#1080)

set `sameSite` to `lax` when allowing insecure cookies (#1078)

🎨 Add color for copy icon (#1070)

Add `ALLOW_INSECURE_COOKIES` feature flag (#1076)

Add phi chat prompt template (#1071)

Bump version to 0.8.3 (#1068)

Remove extra stop token in phi config (#1067)

return only valid models in the API (#1064)

add default value for description and examples in the API route for models (#1063)

add createdAt and udpatedAt to new messages (#1062)

Add website for phi3 in config (#1061)

Reorder models in HuggingChat (#1060)

Add extra stop tokens for phi 3 (#1059)

Add Phi 3 to huggingchat (#1058)

Use llama 3 8B for tasks (#1052)

Final fix to assistants display logic (#1056)

Only require featured assistants for other users' assistants (#1054)

fix: See all your assistants regardless of usercount (#1053)

Use TEI space in prod (#1051)

Support Gemini 1.5 Pro from Vertex AI (#1041)

Move featured assistant check behind `REQUIRE_FEATURED_ASSISTANTS` (#1043)

Use dedicated endpoint for embeddings (#1049)

Always dispose of pipeline for embeddings after use (#1048)

Dispose of embeddings pipeline occasionally to clear memory (#1047)

Docker chown change (#1046)