feat(model): configure Llama-3.1-8B-Instruct with OpenAI-compatible endpoint

feat(tasks): use tools for tasks if available (#1749)

feat(hchat): add QwQ-32B to prod HuggingChat config (#1746)

fix(prod): model config

fix(huggingchat): add additional stop token for model configuration

fix(hchat): update internal endpoint (#1716)

refactor: remove deprecated EXPOSE_API environment variable

fix: handle no beginToken for token based reasoning models (#1713)

feat(hchat): move Llama 3.3 70B as the default model

feat(chart): use inference proxy (#1688)

Update prod.yaml

feat(hchat): Add additional network policy allowed blocks (#1679)

fix(chart): use dedicated nodes (#1675)

feat(hchat): update banners

feat: add `deepseek-ai/DeepSeek-R1-Distill-Qwen-32B` to HuggingChat config (#1660)

fix: update name of task model

feat: show login modal if login is required for creating assistants & tools (#1640)

feat: new tool UI (#1630)

fix: add banner for 3.3

config(hchat): model update 06-12-24 (#1617)

feat: improve tool calling & add tools to qwen 2.5 72b (#1615)

Revert "Remove unneeded QwQ System prompt (#1610)"

Remove unneeded QwQ System prompt (#1610)

feat: UI for advanced reasoning models (#1605)

feat(hchat): add examples to QwQ config and a banner update

feat(hchat): add QwQ to prod config (#1598)

config(hchat): move Qwen 2.5 72B first (#1580)

fix(chart): update network policy (#1578)

feat(chart): add network policy (#1577)

chores(config): add preprompt for Qwen 2.5 coder 32B

fix: use latest blog for qwen 2.5

feat: add `Qwen/Qwen2.5-Coder-32B-Instruct` (#1558)

fix(hchat): config cleanup & fixes

feat(models): lowering temp to 0.5 on Nemotron 70B

fix(cookie): set cookie samesite to lax

fix(models): stop token on nemotron

nemotron: add examples (#1528)

feat(models): add `nvidia/Llama-3.1-Nemotron-70B-Instruct-HF` (#1527)

feat(security): add cookie samesite & security settings (#1517)

feat(security): add flag for allowing iframes (#1518)

Revert "Revert "feat(huggingchat): model config update 25-09-2024 (#1494)""

feat: allow custom message to guest users. (#1441)

Revert "feat(huggingchat): model config update 25-09-2024 (#1494)"

feat(huggingchat): model config update 25-09-2024 (#1494)

feat(huggingchat): Model update 24/09/2024 (#1485)

feat(huggingchat): add default instructions to qwen 2.5 (#1483)

feat(huggingchat): add Qwen 2.5 72B (#1481)

feat(tools): remove feature flag for tools and use env variable instead (#1433)

typo

Update prod.yaml (#1460)