AI/ML stack at a glance
Generally available
Supplier and issuer
From free
Consolidated reference of every model and service the platform uses, what each is for and where. Providers marked currently configured are env-pluggable through the LiteLLM factory.
- Catalogue id
- ai-ml-stack
Description
What it is
Consolidated reference of every model/service mentioned across modules. Providers and models marked "currently configured" are env-pluggable via the LiteLLM factory; dev defaults shown, production paths noted.
Engines
- LiteLLM client and factory The provider abstraction every gateway-side LLM call goes through. Selects Bedrock, Azure OpenAI, OpenAI or Gemini, records per-call cost, latency and tokens, and stamps a prompt hash for replay.
- Embedding service Produces 1024-dim vectors from Cohere Embed v4, OpenAI or bge-m3, all pinned to the same dimensionality so the vectors are interchangeable across providers.
- Mephiston vector database A Rust hybrid dense-and-sparse chunk-level store with tenant isolation, sector and geo filters and a circuit breaker that falls back to Postgres.
- G3 requirement extractor Extracts a tender's individual requirements as claims, with a hallucination harness that requires every item to carry a verified verbatim evidence span.
Keywords
litellm, bedrock, qwen, claude, cohere, bge-m3, pgvector, mephiston, reranker, dspy
Provenance
This page renders a published artifact. Read the same records as JSON if you would rather check the source than the page.