danvics/haiku.rag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
haiku.rag/haiku_rag_slim/haiku/rag
History
Yiorgis Gozadinos aa3e9406cf
auto-append /v1 to per-model Ollama base_url, fix flaky tests
2026-05-04 13:12:37 +03:00
..
agents surface picture image bytes in SearchResult and emit multimodal ToolReturn from the agent search tool 2026-04-30 12:43:05 +03:00
chat bump haiku.skills to 0.16.0 2026-04-28 12:03:14 +03:00
chunkers enable repeat_table_header for self-contained table chunks and docling-serve parity 2026-03-26 14:02:12 +02:00
client make client.search() polymorphic on query type: str | bytes | PIL.Image.Image. Bytes/PIL queries embed via embed_image_query and run vector-only against the chunks table 2026-05-04 11:22:22 +03:00
config add vision: bool flag on ModelConfig (default False). Gate the agent search tool's BinaryContent attachment on qa.model.vision so picture bytes are only sent to vision-capable QA models. 2026-05-04 10:47:21 +03:00
converters add processing.pictures enum (none|description|image), replacing the implicit pair of generate_picture_images+picture_description.enabled flags 2026-04-30 14:26:14 +03:00
embeddings auto-append /v1 to per-model Ollama base_url, fix flaky tests 2026-05-04 13:12:37 +03:00
inspector Migrate LanceDB to native async API 2026-04-24 14:42:52 +03:00
providers retrieve picture image bytes via referenced+zip path, fix docling-serve not returning images even when set to do so. Remove xfail from relevant test 2026-04-30 11:23:29 +03:00
reranking Jina uses AutoModel not AutoModelForSequenceClassification 2026-01-21 11:26:23 +02:00
skill_generator Remove documents from state, fix tests 2026-04-20 09:48:18 +03:00
skills Adapt rag SKILL.md in order to improve citation rate 2026-04-28 14:51:28 +03:00
store make client.search() polymorphic on query type: str | bytes | PIL.Image.Image. Bytes/PIL queries embed via embed_image_query and run vector-only against the chunks table 2026-05-04 11:22:22 +03:00
tools add vision: bool flag on ModelConfig (default False). Gate the agent search tool's BinaryContent attachment on qa.model.vision so picture bytes are only sent to vision-capable QA models. 2026-05-04 10:47:21 +03:00
__init__.py Restructure into uv workspace to support minimal and full installations 2025-11-04 17:59:12 +02:00
app.py expose image-as-query through MCP and the CLI. 2026-05-04 11:46:45 +03:00
cli.py expose image-as-query through MCP and the CLI. 2026-05-04 11:46:45 +03:00
context.py surface picture image bytes in SearchResult and emit multimodal ToolReturn from the agent search tool 2026-04-30 12:43:05 +03:00
logging.py Restructure into uv workspace to support minimal and full installations 2025-11-04 17:59:12 +02:00
mcp.py expose image-as-query through MCP and the CLI. 2026-05-04 11:46:45 +03:00
monitor.py Update dependencies 2026-01-19 16:23:26 +02:00
utils.py auto-append /v1 to per-model Ollama base_url, fix flaky tests 2026-05-04 13:12:37 +03:00