Commit graph

8 commits

Author SHA1 Message Date
Yiorgis Gozadinos
7f7223e0ac
Default to ollama:qwen3.8
Replaces gpt-oss on ModelConfig, qa.model and processing.title_model, and
ministral-3 on the picture-description model. qa.model.vision follows the
model and is now true.

enable_thinking was gated on the gpt-oss name, so it did nothing for
qwen3.8. With title_model's max_tokens of 100 the reasoning consumed the
whole budget and title generation returned an empty string. The mapping
now applies to any ollama model via reasoning_effort(): false sends
"none", true sends "high". Measured on qwen3.8:27b-mlx, "low" does not
disable thinking and "none" does; gpt-oss is the inverse, its template
has no "none" level, so it keeps "low".

Picture description bypasses get_model -- docling posts the request
itself from a params dict -- so the flag was inert on that path too.
vlm_api_params() carries reasoning_effort into both converters' request
bodies. At max_tokens 200 the description survived either way, but the
switch cut completion tokens from 141 to 45.

test_search_tool_skips_binary_content_when_qa_model_is_text_only asserted
the vision default rather than setting it; it now configures vision=False
itself.

docs/benchmarks.md keeps ministral-3: those are recorded measurements.
2026-09-04 12:36:36 +03:00
Yiorgis Gozadinos
2310b7a8b3
Add per-endpoint api_key to model and embedding config 2026-08-23 23:54:40 +03:00
Yiorgis Gozadinos
afd6e3ae00
Share the VLM URL builder and centralize the embedder empty guard 2026-06-29 15:15:26 +03:00
Yiorgis Gozadinos
afd4665517
Thread source_uri through URL ingest 2026-05-12 15:13:02 +03:00
Yiorgis Gozadinos
3149552a61
Add 'plain' format and fallback for text conversion 2025-12-12 18:11:25 +02:00
Yiorgis Gozadinos
06b4f6a224
Add format parameter for text-to-DoclingDocument conversion 2025-12-08 15:56:21 +02:00
Yiorgis Gozadinos
14bdb7cb27
async versions for convert_file() convert_text() 2025-11-26 17:46:25 +02:00
Yiorgis Gozadinos
92def1c6a5
Rebase after haiku.rag-slim migration 2025-11-17 13:05:05 +02:00
Renamed from src/haiku/rag/converters/base.py (Browse further)