WeKnora/config
Frank Zhu acd1a2a5a4
docs(ollama): document embedding model config and RAM guidance (#3531)
* docs(ollama): document embedding model config and RAM guidance (#3480)

Local embedding and generation share the Ollama process at OLLAMA_BASE_URL.
The embedding model name is the local Embedding model's name; EMBEDDING_MODEL_NAME
is read only when builtin_models.yaml references it. The published 8 GB
starting point does not include Ollama weights or optional Neo4j.

Fixes #3480

* docs(ollama): shrink README/docs scope per maintainer review (#3480)
2026-09-23 12:02:42 +08:00
..
prompt_templates fix(agent): allow keyword retry after search_knowledge rerank rejection 2026-09-18 16:06:52 +08:00
agent_type_presets.yaml refactor(agent): consolidate knowledge retrieval tools into search_knowledge, read_document, list_documents (#3381) 2026-09-18 14:12:22 +08:00
builtin_agents.yaml feat(agent): size agent history by the window and calibrate token estimates (#3413) 2026-09-18 22:51:31 +08:00
builtin_models.yaml.example docs(ollama): document embedding model config and RAM guidance (#3531) 2026-09-23 12:02:42 +08:00
config.yaml feat(knowledge): derive knowledge base descriptions from document profiles (#3370) 2026-09-17 22:21:55 +08:00
models.json.example refactor(models): rebuild vendor integration on protocol + catalog + vendor layers (#3470) 2026-09-20 21:28:23 +08:00