From 5a0430857f73e21fe1bb4c5d333ece890572fa8b Mon Sep 17 00:00:00 2001 From: Yiorgis Gozadinos Date: Thu, 5 Mar 2026 15:48:08 +0200 Subject: [PATCH] Enable thinking by default for QA agent --- CHANGELOG.md | 1 + docs/configuration/index.md | 4 ++-- docs/configuration/providers.md | 6 +++--- docs/configuration/qa-research.md | 2 +- haiku_rag_slim/haiku/rag/config/models.py | 2 +- 5 files changed, 8 insertions(+), 7 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index bd55fc13..52fcc00e 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -4,6 +4,7 @@ ### Changed - **Default model temperatures**: Set task-appropriate temperature defaults — 0.3 for QA, research, and title generation; 0.0 for RLM and picture description. Previously unset (provider defaults, typically 0.7–1.0). +- **QA thinking enabled by default**: `enable_thinking` now defaults to `True` for QA agent, improving answer quality with reasoning models. - **Default title max_tokens**: Set `max_tokens=100` for title generation model to keep titles concise - **Evaluation judge**: Set `temperature=0.0` and `enable_thinking=True` for deterministic, higher-quality judging. Removed unused judge config from retrieval benchmarks. - **Test suite cleanup**: Removed stale VCR cassettes, dead fixtures, orphaned directories, and redundant tests. Strengthened weak assertions across search, context enhancement, and converter tests. Relocated misplaced `SearchResult._get_primary_label` test to `test_search.py` diff --git a/docs/configuration/index.md b/docs/configuration/index.md index 917f8e1a..e605c277 100644 --- a/docs/configuration/index.md +++ b/docs/configuration/index.md @@ -44,7 +44,7 @@ qa: model: provider: ollama name: gpt-oss - enable_thinking: false + enable_thinking: true ``` ## Complete Configuration Example @@ -84,7 +84,7 @@ qa: model: provider: ollama name: gpt-oss - enable_thinking: false + enable_thinking: true temperature: 0.3 max_iterations: 2 max_concurrency: 1 diff --git a/docs/configuration/providers.md b/docs/configuration/providers.md index 07cbcf07..cef725e6 100644 --- a/docs/configuration/providers.md +++ b/docs/configuration/providers.md @@ -37,7 +37,7 @@ The `enable_thinking` setting controls whether models use explicit reasoning ste ```yaml qa: model: - enable_thinking: false # Faster responses + enable_thinking: true # Better grounded answers research: model: @@ -63,8 +63,8 @@ See the [Pydantic AI thinking documentation](https://ai.pydantic.dev/thinking/) - **LM Studio**: Models supporting reasoning (gpt-oss, etc.) **When to use:** -- Disable for simple queries, RAG workflows, speed-critical applications -- Enable for complex reasoning, mathematical problems, research tasks +- Enable for QA, research, complex reasoning, and mathematical problems +- Disable for speed-critical applications, title generation, and simple tasks ## Embedding Providers diff --git a/docs/configuration/qa-research.md b/docs/configuration/qa-research.md index 9a72b2bf..8df15be3 100644 --- a/docs/configuration/qa-research.md +++ b/docs/configuration/qa-research.md @@ -31,7 +31,7 @@ qa: model: provider: ollama name: gpt-oss - enable_thinking: false + enable_thinking: true temperature: 0.3 # Default: 0.3 max_iterations: 2 # Maximum search iterations max_concurrency: 1 # Concurrent search operations diff --git a/haiku_rag_slim/haiku/rag/config/models.py b/haiku_rag_slim/haiku/rag/config/models.py index c621b99a..75395d68 100644 --- a/haiku_rag_slim/haiku/rag/config/models.py +++ b/haiku_rag_slim/haiku/rag/config/models.py @@ -75,7 +75,7 @@ class QAConfig(BaseModel): default_factory=lambda: ModelConfig( provider="ollama", name="gpt-oss", - enable_thinking=False, + enable_thinking=True, temperature=0.3, ) )