biblicus 0.15.0__py3-none-any.whl → 0.16.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: biblicus
3
- Version: 0.15.0
3
+ Version: 0.16.0
4
4
  Summary: Command line interface and Python library for corpus ingestion, retrieval, and evaluation.
5
5
  License: MIT
6
6
  Requires-Python: >=3.9
@@ -11,6 +11,7 @@ Requires-Dist: PyYAML>=6.0
11
11
  Requires-Dist: pypdf>=4.0
12
12
  Requires-Dist: Jinja2>=3.1
13
13
  Requires-Dist: dotyaml>=0.1.3
14
+ Requires-Dist: numpy>=1.24
14
15
  Provides-Extra: dev
15
16
  Requires-Dist: behave>=1.2.6; extra == "dev"
16
17
  Requires-Dist: coverage[toml]>=7.0; extra == "dev"
@@ -57,8 +58,15 @@ Dynamic: license-file
57
58
  ![Coverage][coverage-badge]
58
59
  ![Documentation][documentation-badge]
59
60
 
60
- Make your documents usable by your assistant, then decide later how you will search and retrieve them.
61
-
61
+ <p>
62
+ <img
63
+ src="docs/_static/Biblicus-logo.png"
64
+ alt="Biblicus logo"
65
+ align="right"
66
+ width="216"
67
+ />
68
+ Make your documents usable by your assistant, then decide later how you will search and retrieve them.
69
+ </p>
62
70
  If you are building an assistant in Python, you probably have material you want it to use: notes, documents, web pages, and reference files. A common approach is retrieval augmented generation, where a system retrieves relevant material and uses it as evidence when generating a response.
63
71
 
64
72
  The first practical problem is not retrieval. It is collection and care. You need a stable place to put raw items, you need a small amount of metadata so you can find them again, and you need a way to evolve your retrieval approach over time without rewriting ingestion.
@@ -538,7 +546,7 @@ Three backends are included.
538
546
 
539
547
  - `scan` is a minimal baseline that scans raw items directly.
540
548
  - `sqlite-full-text-search` is a practical baseline that builds a full text search index in SQLite.
541
- - `vector` is a deterministic term-frequency vector baseline with cosine similarity scoring.
549
+ - `tf-vector` is a deterministic term-frequency vector baseline with cosine similarity scoring.
542
550
 
543
551
  For detailed documentation including configuration options, performance characteristics, and usage examples, see the [Backend Reference][backend-reference].
544
552
 
@@ -1,25 +1,27 @@
1
- biblicus/__init__.py,sha256=xZ9X4aPjgTWT8Uds5CZ7Y8Tiy9FmryQyO4s4lsF8HWA,496
1
+ biblicus/__init__.py,sha256=VK1nvxxf1NI1u5Ad94yyMpC5Xc_HJ7-3F_TnJdhItbA,496
2
2
  biblicus/__main__.py,sha256=ipfkUoTlocVnrQDM69C7TeBqQxmHVeiWMRaT3G9rtnk,117
3
- biblicus/cli.py,sha256=APxBNLztfGTVGgxt5qgCofYti2AsGGeZQ7SB9tkneXQ,41760
3
+ biblicus/chunking.py,sha256=GdJr0skAAI0Su99mr7dXqCgR7eJ0sJu8n2XesVGyddY,13206
4
+ biblicus/cli.py,sha256=x3bbtg_nzvIZlHmiPp-4L2EtV6wugTMueFTkXQy9y1s,43372
4
5
  biblicus/constants.py,sha256=gAlEVJhxdFj-eWWJrlYbP7H1X3c5gwhrIBq9NQ1Vq_E,371
5
6
  biblicus/context.py,sha256=iXRFGpf_5YDPsDsm_iTK6nCvtUWDoYVI7op-l2QU3uA,10189
6
7
  biblicus/corpus.py,sha256=qSDnYJXhWlF2p_BbFLl6xtI53lIIPxwyKLLGLC432Sg,55612
7
8
  biblicus/crawl.py,sha256=n8rXBMnziBK9vtKQQCXYOpBzqsPCswj2PzVJUb370KY,6250
9
+ biblicus/embedding_providers.py,sha256=phWEsq1vryyTFRRs6uZ0sx9FhrqWIkDsS3I52I64zqM,3839
8
10
  biblicus/errors.py,sha256=uMajd5DvgnJ_-jq5sbeom1GV8DPUc-kojBaECFi6CsY,467
9
11
  biblicus/evaluation.py,sha256=5xWpb-8f49Osh9aHzo1ab3AXOmls3Imc5rdnEC0pN-8,8143
10
12
  biblicus/evidence_processing.py,sha256=sJe6T1nLxvU0xs9yMH8JZZS19zHXMR-Fpr5lWi5ndUM,6120
11
13
  biblicus/extraction.py,sha256=qvrsq6zSz2Kg-cap-18HPHC9pQlqEGo7pyID2uKCyBo,19760
12
14
  biblicus/extraction_evaluation.py,sha256=cBC2B1nQCtXmOcVWUhHyO2NJRX8QSDuqhVjEc8PXrOA,10400
13
- biblicus/frontmatter.py,sha256=JOGjIDzbbOkebQw2RzA-3WDVMAMtJta2INjS4e7-LMg,2463
15
+ biblicus/frontmatter.py,sha256=uFC4iIrgpnTDiP1gvAnT_CbFYdNuUVtETX7tZ3a9g-Y,2517
14
16
  biblicus/hook_logging.py,sha256=IMvde-JhVWrx9tNz3eDJ1CY_rr5Sj7DZ2YNomYCZbz0,5366
15
17
  biblicus/hook_manager.py,sha256=ZCAkE5wLvn4lnQz8jho_o0HGEC9KdQd9qitkAEUQRcw,6997
16
18
  biblicus/hooks.py,sha256=OHQOmOi7rUcQqYWVeod4oPe8nVLepD7F_SlN7O_-BsE,7863
17
19
  biblicus/ignore.py,sha256=fyjt34E6tWNNrm1FseOhgH2MgryyVBQVzxhKL5s4aio,1800
18
20
  biblicus/inference.py,sha256=_k00AIPoXD2lruiTB-JUagtY4f_WKcdzA3axwiq1tck,3512
19
21
  biblicus/knowledge_base.py,sha256=JmlJw8WD_fgstuq1PyWVzU9kzvVzyv7_xOvhS70xwUw,6654
20
- biblicus/models.py,sha256=r28O6cg3d1bjJnKqpLieVLTgtXTfzb_60wMORvVuDN0,15846
22
+ biblicus/models.py,sha256=5AQ6oXK_KJyU0Kyv5ff8yD8nevNKb_6Hjr2_vlRSlK0,16297
21
23
  biblicus/recipes.py,sha256=rqU66QnjOup6O8Y9Yq7XszmpoM0Pyrjw3RrfdnlVqgE,4210
22
- biblicus/retrieval.py,sha256=A1SI4WK5cX-WbtN6FJ0QQxqlEOtQhddLrL0LZIuoTC4,4180
24
+ biblicus/retrieval.py,sha256=GXYT_3RPdqZEYdBQ4F4lIXDOhWw0nfL9bd781bgrn_4,4279
23
25
  biblicus/sources.py,sha256=EFy8-rQNLsyzz-98mH-z8gEHMYbqigcNFKLaR92KfDE,7241
24
26
  biblicus/time.py,sha256=3BSKOSo7R10K-0Dzrbdtl3fh5_yShTYqfdlKvvdkx7M,485
25
27
  biblicus/uris.py,sha256=xXD77lqsT9NxbyzI1spX9Y5a3-U6sLYMnpeSAV7g-nM,2013
@@ -34,17 +36,20 @@ biblicus/ai/llm.py,sha256=g724_UAxmicB_W-Z7Uu9SRsI9-aVNZUlYIjvnlE17VE,4712
34
36
  biblicus/ai/models.py,sha256=6newnT0NJf3uf9FvWXVC-9Gkk5xRB-PjXDZpeBHA04Y,7857
35
37
  biblicus/analysis/__init__.py,sha256=I4LqxfKPKF3DEVmAyagQ8J1RN-ia3fyfKJ9frCllZQE,1385
36
38
  biblicus/analysis/base.py,sha256=gB4ilvyMpiWU1m_ydy2dIHGP96ZFIFvVUL9iVDZKPJM,1265
37
- biblicus/analysis/markov.py,sha256=XiNbfg8lmKWXCzQJhZtZxghT7gBPh2o6xA3D1-tMQqs,61762
39
+ biblicus/analysis/markov.py,sha256=1OESAJYUkk1F3l3DUryrV8Hx1aa6OTPiXCDdgfAg6pU,63168
38
40
  biblicus/analysis/models.py,sha256=FnUAO6n1yjagYlhe2ocRtfb3IZT3W03rrEZ9LdCx7Kc,56214
39
41
  biblicus/analysis/profiling.py,sha256=v2B4Tn9WiXRRP_wIADBPRQVKkMc92KXCas7OBa7n0LU,10670
40
42
  biblicus/analysis/schema.py,sha256=MCiAQJmijVk8iM8rOUYbzyaDwsMR-Oo86iZU5NCbDMM,435
41
43
  biblicus/analysis/topic_modeling.py,sha256=mNBiRMpY5Jtyz8Aj-WXYY8guEghx9jozTfgveinJLoc,22135
42
- biblicus/backends/__init__.py,sha256=3HJY0oMm8pFFVGC4Z-dlPRHhIPVDdUzsa4IMjKP_9dI,1378
44
+ biblicus/backends/__init__.py,sha256=WJSvXc6boEj8PeFr__AC6l_0lfBPJpaVgMbVq30vtZU,1669
43
45
  biblicus/backends/base.py,sha256=Erfj9dXg0nkRKnEcNjHR9_0Ddb2B1NvbmRksVm_g1dU,1776
44
- biblicus/backends/hybrid.py,sha256=FjCzrXdicbM-qVDM-_AHYTT8Gzvem1eZJaQUVKk_tMg,10753
46
+ biblicus/backends/embedding_index_common.py,sha256=WdmnOr8-QaLZH9b7TNmiWg_5auIqDYviXc-twOd7WsM,10216
47
+ biblicus/backends/embedding_index_file.py,sha256=igwlWHuqQD72qyJ3OZ9uyBGeha7AMg6uA3Uu9QD_2_M,9552
48
+ biblicus/backends/embedding_index_inmemory.py,sha256=oZCNS1kMajEj8u9C5iOjs_dAwhZ8ajU_br0F_8onRLY,9457
49
+ biblicus/backends/hybrid.py,sha256=_kqpvD9V6oFdFSXE7K_rTN8qqH-vDIigPDX0uQxFhaM,10828
45
50
  biblicus/backends/scan.py,sha256=hdNnQWqi5IH6j95w30BZHxLJ0W9PTaOkqfWJuxCCEMI,12478
46
- biblicus/backends/sqlite_full_text_search.py,sha256=z0WsURTj4w8Y6SPa6k4bV9wdze-HwNWgxj5qcab0TUE,24480
47
- biblicus/backends/vector.py,sha256=3RdxSBPb1kOX4Sfd4d1qXFW9ecuiRvGpOHadLCbeh1g,15183
51
+ biblicus/backends/sqlite_full_text_search.py,sha256=tkFYdKwH6WvAF3En1fvGN_03Ud0_Z1igGxhUW4meCbA,24496
52
+ biblicus/backends/tf_vector.py,sha256=HFV2aj1i4uxFYBd4GOv2M665ZcaQNgHWA4qmLbpIc4k,15220
48
53
  biblicus/extractors/__init__.py,sha256=ci3oldbdQZ8meAfHccM48CqQtZsPSRg3HkPrBSZF15M,2673
49
54
  biblicus/extractors/base.py,sha256=ka-nz_1zHPr4TS9sU4JfOoY-PJh7lbHPBOEBrbQFGSc,2171
50
55
  biblicus/extractors/deepgram_stt.py,sha256=VI71i4lbE-EFHcvpNcCPRpT8z7A5IuaSrT1UaPyZ8UY,6323
@@ -73,9 +78,9 @@ biblicus/text/prompts.py,sha256=Z5fSsy1Xzr0rCI0WZ3djiEQlbRDncyNBQ7_ZoWVPL4g,6704
73
78
  biblicus/text/redact.py,sha256=tkDRmA0VvOZwMryEmBPLEHf3Z6VHJkkaWjBaNIMyGZ0,8415
74
79
  biblicus/text/slice.py,sha256=dlHxGO8c5P8BszXGwlNQoQ-cyWjJf6PfS1LUBJXXGEE,5762
75
80
  biblicus/text/tool_loop.py,sha256=w1PGLBvIemOdi6l0ArdYDVL7zgx-RC76bBOO0PKqpt0,11831
76
- biblicus-0.15.0.dist-info/licenses/LICENSE,sha256=lw44GXFG_Q0fS8m5VoEvv_xtdBXK26pBcbSPUCXee_Q,1078
77
- biblicus-0.15.0.dist-info/METADATA,sha256=z2HMoYpVwMl30DhbI00Jp1QV4YH680Vz_4GQF3uM_3o,30782
78
- biblicus-0.15.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
79
- biblicus-0.15.0.dist-info/entry_points.txt,sha256=BZmO4H8Uz00fyi1RAFryOCGfZgX7eHWkY2NE-G54U5A,47
80
- biblicus-0.15.0.dist-info/top_level.txt,sha256=sUD_XVZwDxZ29-FBv1MknTGh4mgDXznGuP28KJY_WKc,9
81
- biblicus-0.15.0.dist-info/RECORD,,
81
+ biblicus-0.16.0.dist-info/licenses/LICENSE,sha256=lw44GXFG_Q0fS8m5VoEvv_xtdBXK26pBcbSPUCXee_Q,1078
82
+ biblicus-0.16.0.dist-info/METADATA,sha256=D_qXRDdM_7LnOD-GBtnqwldEWOKjt_uV-TfqvnL8MAU,30933
83
+ biblicus-0.16.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
84
+ biblicus-0.16.0.dist-info/entry_points.txt,sha256=BZmO4H8Uz00fyi1RAFryOCGfZgX7eHWkY2NE-G54U5A,47
85
+ biblicus-0.16.0.dist-info/top_level.txt,sha256=sUD_XVZwDxZ29-FBv1MknTGh4mgDXznGuP28KJY_WKc,9
86
+ biblicus-0.16.0.dist-info/RECORD,,