42 lines
848 B
Text
42 lines
848 B
Text
# haiku.rag configuration for the chat app
|
|
# Copy to haiku.rag.yaml and customize as needed
|
|
|
|
# QA model configuration
|
|
qa:
|
|
model:
|
|
provider: ollama
|
|
name: gpt-oss
|
|
# For Anthropic:
|
|
# provider: anthropic
|
|
# name: claude-sonnet-4-20250514
|
|
# For OpenAI:
|
|
# provider: openai
|
|
# name: gpt-4o
|
|
|
|
# Embedding configuration
|
|
embeddings:
|
|
model:
|
|
provider: ollama
|
|
name: qwen3-embedding:4b
|
|
vector_dim: 2560
|
|
# For OpenAI:
|
|
# provider: openai
|
|
# name: text-embedding-3-small
|
|
# vector_dim: 1536
|
|
|
|
# Optional reranking
|
|
# reranking:
|
|
# model:
|
|
# provider: cohere
|
|
# name: rerank-v3.5
|
|
|
|
# Search settings
|
|
search:
|
|
limit: 5
|
|
context_radius: 0
|
|
|
|
# Provider settings
|
|
providers:
|
|
ollama:
|
|
# Use host.docker.internal to reach Ollama running on the host machine
|
|
base_url: http://host.docker.internal:11434
|