From cc8f7d237ad6c19d957853ebd6b54016b22e472d Mon Sep 17 00:00:00 2001 From: Inferencebot Date: Wed, 7 Oct 2026 09:44:12 -0600 Subject: [PATCH] Add tinfoil/nomic-embed-text embedding model (admin-team scoped, for co-op docs RAG) --- config.yaml | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/config.yaml b/config.yaml index 4c3a855..bc9f602 100644 --- a/config.yaml +++ b/config.yaml @@ -154,6 +154,24 @@ model_list: model_info: mode: audio_speech + # --- Embedding model (Tinfoil, in-TEE) --- + # nomic-embed-text — 768-dim text embeddings for RAG/semantic search. + # NOT a chat model: it powers /v1/embeddings only. Scoped to the admin + # account's team (model_info.team_id) so member keys cannot call it — it is + # an operator resource for the co-op's own docs-RAG, not a member-facing + # model. The portal also filters it out of the chat-facing /v1/models list by + # its `mode: embedding`. Pricing per Tinfoil catalog: $0.05/1M input, $0 out. + - model_name: tinfoil/nomic-embed-text + litellm_params: + model: openai/nomic-embed-text + api_base: http://127.0.0.1:3301/v1 + api_key: os.environ/TINFOIL_API_KEY + model_info: + mode: embedding + team_id: cdfdf422-633f-4432-8893-cffee82a8325 + input_cost_per_token: 0.00000005 + output_cost_per_token: 0.0 + # Fallback: if DeepSeek is down, use GPT-OSS # NOTE: DeepSeek V4.1 Flash is a reasoning model — generations routinely run # longer than 30s. A 30s timeout caused LiteLLM to abandon in-flight DeepSeek