Yiorgis Gozadinos
ff8ad0879c
fix context expansion: respect section boundaries, remove max_context_items
2026-04-20 15:18:16 +03:00
Yiorgis Gozadinos
d2b3ba1b59
rename RLM agent to analysis throughout the codebase
2026-04-17 18:32:01 +03:00
Yiorgis Gozadinos
75c84805b4
Improve judge prompt, QA prompt, and raise max_searches to 5
2026-04-16 12:12:23 +03:00
Yiorgis Gozadinos
b6113bf8ab
replace fixed-radius expansion with section-bounded algorithm
...
Context expansion is now automatic and structure-aware. For structured
documents, expands within the section containing the match. For sections
that exceed the budget or are too small, expands item-by-item outward
skipping noise labels. Unstructured documents use budget-based outward
expansion. Results sorted by relevance score.
2026-04-16 12:11:53 +03:00
Yiorgis Gozadinos
110accb8e7
Add ConnectionMode enum (LOCAL/CLOUD/OBJECT_STORAGE) and connect_lancedb() utility to support S3, GCS, Azure, and HDFS backends via storage_options.
2026-04-08 14:19:09 +03:00
Yiorgis Gozadinos
45e94ec67a
Set search limit to 10
2026-03-11 12:26:41 +02:00
Yiorgis Gozadinos
e2749ad2a6
Cap QA agent search iterations to reduce response time
2026-03-11 12:13:43 +02:00
Yiorgis Gozadinos
5a0430857f
Enable thinking by default for QA agent
2026-03-05 15:48:08 +02:00
Yiorgis Gozadinos
3cc2d5e19e
Set appropriate temperature and max_tokens defaults
2026-03-05 13:23:50 +02:00
Yiorgis Gozadinos
ae3469b282
add automatic title generation for documents
2026-02-25 17:12:24 +02:00
Yiorgis Gozadinos
c61ded1271
Replace Docker sandbox with pydantic-monty
2026-02-24 09:55:40 +02:00
Yiorgis Gozadinos
720f697a48
Cleanup
2026-02-06 12:07:21 +01:00
Yiorgis Gozadinos
b426827fc2
Docker-based sandbox. Reused within a single rlm() call for latency
2026-02-06 12:07:19 +01:00
Yiorgis Gozadinos
b68b2393e9
Integrate with client, cli, app, mcp
2026-02-06 12:07:03 +01:00
Yiorgis Gozadinos
ac76ecee86
Remove dead code from iterative research planning refactor
2026-01-31 10:51:34 +02:00
Yiorgis Gozadinos
62d35d2907
Add ocr_engine field to ConversionOptions
2026-01-20 13:41:43 +02:00
Yiorgis Gozadinos
447e94c5db
Config options for generating page images
2026-01-14 11:55:08 +02:00
Yiorgis Gozadinos
bb61e8fab6
Remove custom AG-UI infrastructure in favor of pydantic-ai native support
2026-01-12 12:37:07 +02:00
Yiorgis Gozadinos
f861664656
Extract shared DoclingServeClient for async workflow & use it for VLM support, chunking, converting
2026-01-07 11:09:23 +02:00
Yiorgis Gozadinos
769e0d4746
Update picture description prompt, move its config under prompts
2026-01-07 11:09:23 +02:00
Yiorgis Gozadinos
3c4116397d
Add VLM picture description support for image handling
2026-01-07 11:09:22 +02:00
Yiorgis Gozadinos
08fb99c6f8
Add prompt customization and domain preable
2025-12-26 13:34:51 +02:00
Yiorgis Gozadinos
958fe43f2a
Remove vllm and lmstudio custom configs, they can now use the openai base
2025-12-26 12:02:55 +02:00
Yiorgis Gozadinos
3141c91023
Add base_url to ModelConfig and EmbeddingModelConfig. Deprecate vllm and lm_studio configs, now through open ai
2025-12-24 12:33:44 +02:00
Yiorgis Gozadinos
2161727716
Add auto_vacuum config option to control automatic vacuuming
2025-12-10 11:42:14 +02:00
Yiorgis Gozadinos
68457f251e
Do not generate base64 images by default
2025-12-09 18:42:56 +02:00
Yiorgis Gozadinos
5a593e928e
Set max_context_items to 10
2025-12-09 12:47:42 +02:00
Yiorgis Gozadinos
802f058205
Move search related config under SearchConfig
2025-12-09 12:28:28 +02:00
Yiorgis Gozadinos
4da50873bd
Make search limit configurable
2025-12-09 11:46:43 +02:00
Yiorgis Gozadinos
9a5f8e4368
Add type-aware context expansion for search results
2025-12-08 15:56:21 +02:00
Yiorgis Gozadinos
17c7147a49
Remove pre-processor, no longer needed
2025-12-08 15:56:01 +02:00
Yiorgis Gozadinos
3525fae625
Use EmbeddingModelConfig similar to ModelConfig for embeddings
2025-12-02 11:55:31 +02:00
Yiorgis Gozadinos
0303e6a8cd
Support LMStudio
2025-11-26 10:31:40 +02:00
Yiorgis Gozadinos
e83978f88b
Revert embeddings to use flat config
2025-11-25 12:51:58 +02:00
Yiorgis Gozadinos
ba4dddeeaf
Make thinking false by default
2025-11-25 12:35:38 +02:00
Yiorgis Gozadinos
a9701616c8
Rename model to name under model
2025-11-25 12:28:43 +02:00
Yiorgis Gozadinos
1bb7b6d5bd
Add support for per-model configuration settings including thinking, temperature and max_tokens
2025-11-25 12:14:24 +02:00
Yiorgis Gozadinos
8c02e865c7
Change default embedding model to qwen3-embedding:4b
2025-11-21 16:30:41 +02:00
Yiorgis Gozadinos
6d8ab2575d
Clarify refine_factor, set default to 30
2025-11-21 15:53:24 +02:00
Yiorgis Gozadinos
6a2f33b464
Create vector index from CLI, use configurable refine_factor
2025-11-21 13:54:01 +02:00
Yiorgis Gozadinos
0bb3f4301c
Additional options for document conversion with docling
2025-11-18 15:44:04 +02:00
Yiorgis Gozadinos
75cbdb47a8
Add chunker configuration options
...
- Add `chunker_type` config field to choose between "hybrid" (default) and "hierarchical" chunking strategies
- Add `chunking_merge_peers` config field for HybridChunker (default: true)
- Add `chunking_use_markdown_tables` config field to control table serialization format (default: false, matching docling's default)
2025-11-17 13:05:06 +02:00
Yiorgis Gozadinos
de5bb117fe
Chunker abstraction
2025-11-17 13:05:06 +02:00
Yiorgis Gozadinos
541552215e
Switch to using HuggingFace tokenizers
2025-11-17 13:05:05 +02:00
Yiorgis Gozadinos
7ba1c2376e
Introduce converters for supporting more than local docling document conversion. Transform existing FileReader and utils to "docling-local" converter
2025-11-17 13:05:05 +02:00
Yiorgis Gozadinos
4599dd1481
Drop disable_auto_create flag, simply create only on write operations
2025-11-13 13:53:11 +02:00
Yiorgis Gozadinos
8e802d4a91
Default vacuum_retention_seconds increased from 60 seconds to 86400 seconds (1 day) for better version retention in typical workflows
2025-11-13 13:31:53 +02:00
Yiorgis Gozadinos
60ef8fe04c
AGUI starlette server
2025-11-13 13:22:02 +02:00
Yiorgis Gozadinos
b6650d0486
Introduce delete_orphans in monitor (default=false) to delete db entries that do not resolve in the filesystem
2025-11-07 14:40:13 +02:00
Yiorgis Gozadinos
9ee64a33e0
Remove A2A from haiku.rag, turn it into an example
2025-11-07 13:31:51 +02:00
