Yiorgis Gozadinos
|
2f42b1a3ac
|
Get adjacent chunks method
|
2025-08-12 13:24:04 +02:00 |
|
Yiorgis Gozadinos
|
842e4a882d
|
Make citations optional, through cite parameter
|
2025-08-12 13:19:11 +02:00 |
|
Yiorgis Gozadinos
|
5103e6c2d7
|
Add Ollama reranker
|
2025-08-10 20:50:17 +02:00 |
|
Yiorgis Gozadinos
|
8d98eed2e2
|
Make mxbai reranker optional. Only use a reranker if mxbai or cohere are installed
|
2025-08-10 19:49:14 +02:00 |
|
Yiorgis Gozadinos
|
ad4b655a31
|
Operate on DoclingDocument instead of Document
|
2025-08-08 17:24:34 +02:00 |
|
Yiorgis Gozadinos
|
6a3c85e6ae
|
text_to_docling_document() util
|
2025-08-08 15:38:57 +02:00 |
|
Yiorgis Gozadinos
|
b92f25d6fb
|
Make FileReader return a DoclingDocument instead of a md string
|
2025-08-08 14:45:24 +02:00 |
|
Yiorgis Gozadinos
|
b428cb4c5d
|
Forgotten test for FileReader
|
2025-08-01 16:41:24 +02:00 |
|
Yiorgis Gozadinos
|
91f6122ef7
|
Basic chunking using docling
|
2025-08-01 16:27:44 +02:00 |
|
Yiorgis Gozadinos
|
74eea9284a
|
create_document now optionally accepts pre-computed chunks
|
2025-07-26 10:42:27 +03:00 |
|
Yiorgis Gozadinos
|
dfe23482da
|
Tune parameters
|
2025-07-20 22:45:24 +03:00 |
|
Yiorgis Gozadinos
|
c1d5334804
|
Update benchmarks with reranking
|
2025-07-19 19:02:47 +03:00 |
|
Yiorgis Gozadinos
|
2343ab7751
|
Return tuple (Chunk, score,) in rerank()
|
2025-07-19 12:16:17 +03:00 |
|
Yiorgis Gozadinos
|
f25416b0ff
|
Properly test cohere reranker
|
2025-07-18 20:55:28 +03:00 |
|
Yiorgis Gozadinos
|
044e1b0a06
|
mixedbread reranker as default
|
2025-07-18 20:29:24 +03:00 |
|
Yiorgis Gozadinos
|
859860318a
|
Cohere reranker
|
2025-07-17 13:17:16 +03:00 |
|
Yiorgis Gozadinos
|
0bf5606117
|
Store haiku.rag version, enabling upgrades
|
2025-07-16 18:21:41 +03:00 |
|
Yiorgis Gozadinos
|
a2e0f2cefd
|
Remove Claude nonsense, use context manager
|
2025-07-12 23:00:49 +03:00 |
|
Yiorgis Gozadinos
|
62a519b094
|
Prevent rebuild from throwing and recreate the embeddings table
|
2025-07-12 21:21:14 +03:00 |
|
Yiorgis Gozadinos
|
4444ec50da
|
Check if settings are compatible when loading a db
|
2025-07-12 20:56:49 +03:00 |
|
Yiorgis Gozadinos
|
a59b38158d
|
Settings table & repo, tests
|
2025-07-12 20:21:34 +03:00 |
|
Yiorgis Gozadinos
|
42e62f92a1
|
Better formatting of benchmark script
|
2025-07-09 10:27:32 +03:00 |
|
Yiorgis Gozadinos
|
9d72a158a6
|
Document benchmarks
|
2025-07-08 19:01:54 +03:00 |
|
Yiorgis Gozadinos
|
bea96f1b1b
|
Better prompts
|
2025-07-04 13:29:51 +03:00 |
|
Yiorgis Gozadinos
|
1705e7a21c
|
Honour QA_MODEL for anthropic and OpenAI
|
2025-07-04 12:14:13 +03:00 |
|
Yiorgis Gozadinos
|
e66c160055
|
Support for anthropic in Question/Answering
|
2025-07-04 11:55:03 +03:00 |
|
Yiorgis Gozadinos
|
85443ee963
|
Turn rebuild into a generator, track progress in command line
|
2025-07-02 11:10:31 +03:00 |
|
Yiorgis Gozadinos
|
11d9f2701e
|
Rebuild database in client & cli
|
2025-07-02 10:55:06 +03:00 |
|
Yiorgis Gozadinos
|
e5d8396d1b
|
Merge pull request #5 from ggozad/feat/qa
Question/Answering using LLMs
|
2025-06-28 09:41:55 +03:00 |
|
Yiorgis Gozadinos
|
85b106c461
|
OpenAI Question/Answer agent
|
2025-06-28 09:11:39 +03:00 |
|
Yiorgis Gozadinos
|
f3ed88b970
|
Include document uri and meta in search results
|
2025-06-28 09:10:23 +03:00 |
|
Yiorgis Gozadinos
|
ca45f8e5d4
|
Fix db path
|
2025-06-25 19:01:57 +03:00 |
|
Yiorgis Gozadinos
|
2855dd7c13
|
Use LLM-as-a-judge to test QA
|
2025-06-25 18:18:28 +03:00 |
|
Yiorgis Gozadinos
|
26900d9687
|
Run simple benchmarks
|
2025-06-25 18:18:28 +03:00 |
|
Yiorgis Gozadinos
|
c4c670bc40
|
Use proper mocks instead of setattr to satisfy typing. Fix minor typos
|
2025-06-25 17:50:19 +03:00 |
|
Russ Ferriday
|
94ff11ad25
|
feat(tests): Add tests for app and cli modules
|
2025-06-24 23:00:18 +01:00 |
|
Yiorgis Gozadinos
|
3c98f246b5
|
Merge pull request #2 from ggozad/feat/monitor
File monitoring support
|
2025-06-20 10:30:40 +02:00 |
|
Yiorgis Gozadinos
|
27f65adda7
|
Test FileWatcher
|
2025-06-20 09:35:20 +02:00 |
|
Yiorgis Gozadinos
|
ee57bc0a82
|
Use path.as_uri() instead of path.resolve()
|
2025-06-20 09:27:01 +02:00 |
|
Yiorgis Gozadinos
|
943cf3c5e0
|
Rename EMBDEDDING->EMBEDDINGS in env vars
|
2025-06-19 17:44:42 +02:00 |
|
Yiorgis Gozadinos
|
d89b2f1306
|
Test openai voyageai embedders
|
2025-06-19 17:39:04 +02:00 |
|
Yiorgis Gozadinos
|
51723308ed
|
Introduce embedder factory
|
2025-06-18 08:26:11 +02:00 |
|
Yiorgis Gozadinos
|
1e0b6b18aa
|
Add a context manager to the client
|
2025-06-17 12:48:26 +02:00 |
|
Yiorgis Gozadinos
|
6321cfb7a8
|
Add search to client
|
2025-06-17 12:41:37 +02:00 |
|
Yiorgis Gozadinos
|
0b43c7dc7f
|
Handle files/url updates and store md5 hash in the meta
|
2025-06-17 12:22:00 +02:00 |
|
Yiorgis Gozadinos
|
11fd4d75ad
|
Handle files/url with create_document_from_source in client
|
2025-06-17 11:26:02 +02:00 |
|
Yiorgis Gozadinos
|
a91249c575
|
Basic client
|
2025-06-17 10:48:40 +02:00 |
|
Yiorgis Gozadinos
|
1ff17c2f50
|
Add uri to Documents
|
2025-06-17 10:41:44 +02:00 |
|
Yiorgis Gozadinos
|
0b5f89ebad
|
FTS and hybrid search using Reciprocal Rank Fusion
|
2025-06-16 19:28:45 +02:00 |
|
Yiorgis Gozadinos
|
892d1a378d
|
test search
|
2025-06-16 18:10:03 +02:00 |
|