fix(huggingchat): remove app banners (#1426)

build(config): remove 405B from prod config (#1422)

fix(hchat): casing on official tool names

chores(deps): update Transformers to latest version and remove chat templates for all models (#1414)

feat(tools): add FLUX schnell as default image generation tool on HuggingChat

fix(models): correct context window for 405B

fix(featureflags): use correct env vars (#1405)

Community tools (#1250)

fix(featureflags): rewrite feature flag system

Revert "try(auth): fix early access flagging?"

try(auth): fix early access flagging?

fix(config): remove preprompt for huggingchat llama 3.1 (#1358)

feat(auth): Add admin & early access flags based on orgs membership (#1365)

feat(config): improve sampling params for llama 3.1 (#1357)

feat(models): Llama 3.1 support (#1355)

fix(models): Update tokenizer on command R+ (#1345)

fix: prod registry repository (#1340)

remove-internal registry (#1336)

perf: add prod deployment resources (#1333)

Remove Gemma 2 from HuggingChat (#1319)

feat: allow disabling metrics server, consolidate exit handlers (#1201)

Sampling parameters gemma 2

Reduce temp on gemma 2 a bit

Model update 27-06-24 (#1313)

Revert "Request less `max_new_tokens` on tools and reduce `truncate` on CMD R+ (#1292)"

Request less `max_new_tokens` on tools and reduce `truncate` on CMD R+ (#1292)

feat(chart): auto reload when secrets change (#1285)

fix(chart): infisical secret name (#1284)

feat(chart): use infisical (#1276)

Reduce context window on zephyr orpo (#1272)

Revert "Revert "Remove `BODY_SIZE_LIMIT`""

Revert "Remove `BODY_SIZE_LIMIT`"

Remove `BODY_SIZE_LIMIT`

Use bytes for body size limit (#1268)

Add body size limit to prod env (#1265)

feat(chart): service account (#1252)

Use the chat template from tokenizer for `01-ai/Yi-1.5-34B-Chat`

Fix issue with system preprompt and tools (#1198)

Set tools back to true (#1194)

Bypass spaces tools rate limit (#1167)

Improve helm chart (#1144)

fix(chart): incresase resources (#1175)

Hide tools on prod for now (#1165)

[cohere] reduce max_new_tokens (#1160)

Function calling (#996)

Revert "Uses temperature 0.0 for Phi-3." (#1152)

Uses temperature 0.0 for Phi-3. (#1132)

Update examples for Yi (#1150)

Add 01-ai/Yi-1.5-34B-Chat (#1145)

Make messages before login a aws param (#1130)