litdb 2.2.3__tar.gz → 2.2.4__tar.gz
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.
- {litdb-2.2.3/src/litdb.egg-info → litdb-2.2.4}/PKG-INFO +16 -10
- {litdb-2.2.3 → litdb-2.2.4}/README.org +10 -2
- {litdb-2.2.3 → litdb-2.2.4}/pyproject.toml +19 -10
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/app.py +65 -54
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/audio.py +12 -11
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/chat.py +9 -5
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/cli.py +9 -12
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/coa.py +8 -11
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/commands/data_processing.py +3 -3
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/commands/export.py +2 -3
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/commands/filters.py +5 -2
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/commands/install.py +1 -2
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/commands/manage.py +8 -8
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/commands/openalex_commands.py +2 -3
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/commands/research_commands.py +12 -12
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/commands/review.py +0 -1
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/commands/search.py +39 -19
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/commands/tags.py +0 -1
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/crawl.py +8 -9
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/db.py +25 -23
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/doe_collaborators.py +6 -7
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/extract.py +9 -10
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/gpt.py +10 -4
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/images.py +7 -5
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/lab.py +2 -1
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/lsearch.py +3 -2
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/mcp_server.py +20 -17
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/openalex.py +12 -7
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/server.py +1 -2
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/summary.py +5 -5
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/utils.py +2 -1
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/youtube.py +2 -1
- {litdb-2.2.3 → litdb-2.2.4/src/litdb.egg-info}/PKG-INFO +16 -10
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb.egg-info/requires.txt +4 -7
- {litdb-2.2.3 → litdb-2.2.4}/LICENSE +0 -0
- {litdb-2.2.3 → litdb-2.2.4}/setup.cfg +0 -0
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/__init__.py +2 -2
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/bibtex.py +0 -0
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/commands/__init__.py +0 -0
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/commands/utilities.py +1 -1
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/pdf.py +2 -2
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb/research.py +4 -4
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb.egg-info/SOURCES.txt +0 -0
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb.egg-info/dependency_links.txt +0 -0
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb.egg-info/entry_points.txt +0 -0
- {litdb-2.2.3 → litdb-2.2.4}/src/litdb.egg-info/top_level.txt +0 -0
|
@@ -1,11 +1,12 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: litdb
|
|
3
|
-
Version: 2.2.
|
|
3
|
+
Version: 2.2.4
|
|
4
4
|
Summary: A literature database tool with GPT integration.
|
|
5
5
|
Author-email: John Kitchin <jkitchin@andrew.cmu.edu>
|
|
6
6
|
Maintainer-email: John Kitchin <jkitchin@andrew.cmu.edu>
|
|
7
7
|
License-Expression: MIT
|
|
8
8
|
Project-URL: Homepage, https://github.com/jkitchin/litdb
|
|
9
|
+
Requires-Python: >=3.11
|
|
9
10
|
Description-Content-Type: text/plain
|
|
10
11
|
License-File: LICENSE
|
|
11
12
|
Requires-Dist: toml
|
|
@@ -36,14 +37,13 @@ Requires-Dist: pillow
|
|
|
36
37
|
Requires-Dist: bibtexparser<2
|
|
37
38
|
Requires-Dist: pandas
|
|
38
39
|
Requires-Dist: more-itertools
|
|
39
|
-
Requires-Dist: nameparser
|
|
40
|
+
Requires-Dist: nameparser<3
|
|
40
41
|
Requires-Dist: tabulate
|
|
41
42
|
Requires-Dist: IPython
|
|
42
43
|
Requires-Dist: gmft
|
|
43
|
-
Requires-Dist: ruff>=0.13.3
|
|
44
44
|
Requires-Dist: torch
|
|
45
45
|
Requires-Dist: torchvision
|
|
46
|
-
Requires-Dist:
|
|
46
|
+
Requires-Dist: mcp<2,>=1.22
|
|
47
47
|
Provides-Extra: test
|
|
48
48
|
Requires-Dist: pytest>=8.0.0; extra == "test"
|
|
49
49
|
Requires-Dist: pytest-cov>=4.1.0; extra == "test"
|
|
@@ -60,7 +60,6 @@ Requires-Dist: langchain_google_genai; extra == "research"
|
|
|
60
60
|
Requires-Dist: langchain_anthropic; extra == "research"
|
|
61
61
|
Requires-Dist: mistune; extra == "research"
|
|
62
62
|
Requires-Dist: htmldocx; extra == "research"
|
|
63
|
-
Requires-Dist: docx; extra == "research"
|
|
64
63
|
Requires-Dist: md2pdf; extra == "research"
|
|
65
64
|
Requires-Dist: pypandoc; extra == "research"
|
|
66
65
|
Provides-Extra: app
|
|
@@ -75,7 +74,7 @@ Provides-Extra: image
|
|
|
75
74
|
Requires-Dist: pyperclip; extra == "image"
|
|
76
75
|
Requires-Dist: pillow_heif; extra == "image"
|
|
77
76
|
Provides-Extra: mcp
|
|
78
|
-
Requires-Dist: mcp[cli]; extra == "mcp"
|
|
77
|
+
Requires-Dist: mcp[cli]<2,>=1.22; extra == "mcp"
|
|
79
78
|
Provides-Extra: audio
|
|
80
79
|
Requires-Dist: pyaudio; extra == "audio"
|
|
81
80
|
Requires-Dist: SpeechRecognition; extra == "audio"
|
|
@@ -88,7 +87,6 @@ Requires-Dist: langchain_google_genai; extra == "all"
|
|
|
88
87
|
Requires-Dist: langchain_anthropic; extra == "all"
|
|
89
88
|
Requires-Dist: mistune; extra == "all"
|
|
90
89
|
Requires-Dist: htmldocx; extra == "all"
|
|
91
|
-
Requires-Dist: docx; extra == "all"
|
|
92
90
|
Requires-Dist: md2pdf; extra == "all"
|
|
93
91
|
Requires-Dist: pypandoc; extra == "all"
|
|
94
92
|
Requires-Dist: streamlit; extra == "all"
|
|
@@ -98,7 +96,7 @@ Requires-Dist: scrapy; extra == "all"
|
|
|
98
96
|
Requires-Dist: backoff; extra == "all"
|
|
99
97
|
Requires-Dist: pyperclip; extra == "all"
|
|
100
98
|
Requires-Dist: pillow_heif; extra == "all"
|
|
101
|
-
Requires-Dist: mcp[cli]; extra == "all"
|
|
99
|
+
Requires-Dist: mcp[cli]<2,>=1.22; extra == "all"
|
|
102
100
|
Requires-Dist: pyaudio; extra == "all"
|
|
103
101
|
Requires-Dist: SpeechRecognition; extra == "all"
|
|
104
102
|
Dynamic: license-file
|
|
@@ -111,9 +109,17 @@ Dynamic: license-file
|
|
|
111
109
|
<a href="https://github.com/jkitchin/litdb/actions/workflows/build.yml">
|
|
112
110
|
<img src="https://github.com/jkitchin/litdb/actions/workflows/build.yml/badge.svg" alt="Build Status">
|
|
113
111
|
</a>
|
|
114
|
-
<
|
|
112
|
+
<a href="https://github.com/jkitchin/litdb/actions/workflows/test.yml">
|
|
113
|
+
<img src="https://github.com/jkitchin/litdb/actions/workflows/test.yml/badge.svg" alt="CI">
|
|
114
|
+
</a>
|
|
115
|
+
<a href="https://pypi.org/project/litdb/">
|
|
116
|
+
<img src="https://img.shields.io/pypi/v/litdb.svg" alt="PyPI">
|
|
117
|
+
</a>
|
|
118
|
+
<a href="https://pepy.tech/projects/litdb">
|
|
119
|
+
<img src="https://static.pepy.tech/personalized-badge/litdb?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=GREEN&left_text=downloads" alt="PyPI Downloads">
|
|
120
|
+
</a>
|
|
115
121
|
<a href="https://doi.org/10.5281/zenodo.23514948">
|
|
116
|
-
<img src="https://
|
|
122
|
+
<img src="https://img.shields.io/badge/DOI-10.5281%2Fzenodo.23514948-blue.svg" alt="DOI">
|
|
117
123
|
</a>
|
|
118
124
|
#+END_HTML
|
|
119
125
|
|
|
@@ -6,9 +6,17 @@
|
|
|
6
6
|
<a href="https://github.com/jkitchin/litdb/actions/workflows/build.yml">
|
|
7
7
|
<img src="https://github.com/jkitchin/litdb/actions/workflows/build.yml/badge.svg" alt="Build Status">
|
|
8
8
|
</a>
|
|
9
|
-
<
|
|
9
|
+
<a href="https://github.com/jkitchin/litdb/actions/workflows/test.yml">
|
|
10
|
+
<img src="https://github.com/jkitchin/litdb/actions/workflows/test.yml/badge.svg" alt="CI">
|
|
11
|
+
</a>
|
|
12
|
+
<a href="https://pypi.org/project/litdb/">
|
|
13
|
+
<img src="https://img.shields.io/pypi/v/litdb.svg" alt="PyPI">
|
|
14
|
+
</a>
|
|
15
|
+
<a href="https://pepy.tech/projects/litdb">
|
|
16
|
+
<img src="https://static.pepy.tech/personalized-badge/litdb?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=GREEN&left_text=downloads" alt="PyPI Downloads">
|
|
17
|
+
</a>
|
|
10
18
|
<a href="https://doi.org/10.5281/zenodo.23514948">
|
|
11
|
-
<img src="https://
|
|
19
|
+
<img src="https://img.shields.io/badge/DOI-10.5281%2Fzenodo.23514948-blue.svg" alt="DOI">
|
|
12
20
|
</a>
|
|
13
21
|
#+END_HTML
|
|
14
22
|
|
|
@@ -7,7 +7,7 @@ where = ["src"]
|
|
|
7
7
|
|
|
8
8
|
[project]
|
|
9
9
|
name = "litdb"
|
|
10
|
-
version = "2.2.
|
|
10
|
+
version = "2.2.4"
|
|
11
11
|
authors = [
|
|
12
12
|
{name = "John Kitchin", email = "jkitchin@andrew.cmu.edu"},
|
|
13
13
|
]
|
|
@@ -16,6 +16,7 @@ maintainers = [
|
|
|
16
16
|
]
|
|
17
17
|
description = "A literature database tool with GPT integration."
|
|
18
18
|
license = "MIT"
|
|
19
|
+
requires-python = ">=3.11"
|
|
19
20
|
readme = {file = "README.org", content-type = "text/plain"}
|
|
20
21
|
dependencies = [
|
|
21
22
|
# Core dependencies - always installed
|
|
@@ -48,16 +49,20 @@ dependencies = [
|
|
|
48
49
|
# Data processing and COA
|
|
49
50
|
"pandas",
|
|
50
51
|
"more-itertools",
|
|
51
|
-
"nameparser",
|
|
52
|
+
"nameparser<3", # 3.0 removed HumanName (used in coa.py, doe_collaborators.py)
|
|
52
53
|
"tabulate",
|
|
53
54
|
"IPython",
|
|
54
55
|
# Table extraction
|
|
55
56
|
"gmft",
|
|
56
|
-
# Development tools
|
|
57
|
-
"ruff>=0.13.3",
|
|
58
57
|
"torch",
|
|
59
58
|
"torchvision",
|
|
60
|
-
|
|
59
|
+
# mcp 2.x removed mcp.server.fastmcp, which mcp_server.py uses
|
|
60
|
+
"mcp>=1.22,<2",
|
|
61
|
+
]
|
|
62
|
+
|
|
63
|
+
[dependency-groups]
|
|
64
|
+
dev = [
|
|
65
|
+
"ruff>=0.17.5",
|
|
61
66
|
]
|
|
62
67
|
|
|
63
68
|
[project.scripts]
|
|
@@ -91,7 +96,6 @@ research = [
|
|
|
91
96
|
"langchain_anthropic",
|
|
92
97
|
"mistune",
|
|
93
98
|
"htmldocx",
|
|
94
|
-
"docx",
|
|
95
99
|
"md2pdf",
|
|
96
100
|
"pypandoc",
|
|
97
101
|
]
|
|
@@ -121,7 +125,7 @@ image = [
|
|
|
121
125
|
|
|
122
126
|
# MCP server for Claude Desktop
|
|
123
127
|
mcp = [
|
|
124
|
-
"mcp[cli]",
|
|
128
|
+
"mcp[cli]>=1.22,<2",
|
|
125
129
|
]
|
|
126
130
|
|
|
127
131
|
# Audio recording and transcription (requires external libraries)
|
|
@@ -140,7 +144,6 @@ all = [
|
|
|
140
144
|
"langchain_anthropic",
|
|
141
145
|
"mistune",
|
|
142
146
|
"htmldocx",
|
|
143
|
-
"docx",
|
|
144
147
|
"md2pdf",
|
|
145
148
|
"pypandoc",
|
|
146
149
|
"streamlit",
|
|
@@ -150,7 +153,7 @@ all = [
|
|
|
150
153
|
"backoff",
|
|
151
154
|
"pyperclip",
|
|
152
155
|
"pillow_heif",
|
|
153
|
-
"mcp[cli]",
|
|
156
|
+
"mcp[cli]>=1.22,<2",
|
|
154
157
|
"pyaudio",
|
|
155
158
|
"SpeechRecognition",
|
|
156
159
|
]
|
|
@@ -201,4 +204,10 @@ exclude_lines = [
|
|
|
201
204
|
directory = "htmlcov"
|
|
202
205
|
|
|
203
206
|
# (shell-command "uv build")
|
|
204
|
-
# (shell-command "uv publish")
|
|
207
|
+
# (shell-command "uv publish")
|
|
208
|
+
[tool.ruff.lint.per-file-ignores]
|
|
209
|
+
# The Streamlit UI and the MCP tools are top-level boundaries: any error is
|
|
210
|
+
# shown to the user (st.error / tool result) instead of crashing the page or
|
|
211
|
+
# server, and optional metadata parsing falls back silently.
|
|
212
|
+
"src/litdb/app.py" = ["BLE001", "S110"]
|
|
213
|
+
"src/litdb/mcp_server.py" = ["BLE001"]
|
|
@@ -190,7 +190,7 @@ def format_citation(extra):
|
|
|
190
190
|
parts = []
|
|
191
191
|
|
|
192
192
|
# Authors
|
|
193
|
-
if
|
|
193
|
+
if data.get("authorships"):
|
|
194
194
|
authors = [a["author"]["display_name"] for a in data["authorships"][:3]]
|
|
195
195
|
if len(data["authorships"]) > 3:
|
|
196
196
|
authors.append("et al.")
|
|
@@ -303,7 +303,7 @@ def tab_search():
|
|
|
303
303
|
try:
|
|
304
304
|
extra_data = json.loads(extra)
|
|
305
305
|
doi = extra_data.get("doi") or extra_data.get("id")
|
|
306
|
-
if doi and (doi.startswith("http"
|
|
306
|
+
if doi and (doi.startswith(("http", "10."))):
|
|
307
307
|
dois_to_process.append(doi)
|
|
308
308
|
except Exception:
|
|
309
309
|
pass
|
|
@@ -405,8 +405,8 @@ Adding: references, citations, and related works...
|
|
|
405
405
|
# Execute query if needed
|
|
406
406
|
if should_run_query:
|
|
407
407
|
# Vector search - we need to compute embedding first
|
|
408
|
-
from sentence_transformers import SentenceTransformer
|
|
409
408
|
import numpy as np
|
|
409
|
+
from sentence_transformers import SentenceTransformer
|
|
410
410
|
|
|
411
411
|
config = get_config()
|
|
412
412
|
model = SentenceTransformer(config["embedding"]["model"])
|
|
@@ -477,10 +477,11 @@ Adding: references, citations, and related works...
|
|
|
477
477
|
cols = st.columns(len(current_tags) + 1)
|
|
478
478
|
for idx, tag in enumerate(current_tags):
|
|
479
479
|
with cols[idx]:
|
|
480
|
-
if st.button(
|
|
481
|
-
|
|
482
|
-
|
|
483
|
-
|
|
480
|
+
if st.button(
|
|
481
|
+
f"🗑️ {tag}", key=f"rm_tag_v_{i}_{tag}"
|
|
482
|
+
) and remove_tag_from_source(source, tag):
|
|
483
|
+
st.success(f"Removed tag: {tag}")
|
|
484
|
+
st.rerun()
|
|
484
485
|
else:
|
|
485
486
|
st.caption("No tags yet")
|
|
486
487
|
|
|
@@ -494,13 +495,16 @@ Adding: references, citations, and related works...
|
|
|
494
495
|
label_visibility="collapsed",
|
|
495
496
|
)
|
|
496
497
|
with new_tag_col2:
|
|
497
|
-
if
|
|
498
|
-
|
|
499
|
-
|
|
500
|
-
|
|
501
|
-
|
|
502
|
-
|
|
503
|
-
|
|
498
|
+
if (
|
|
499
|
+
st.button("➕ Add", key=f"add_tag_v_{i}")
|
|
500
|
+
and new_tag
|
|
501
|
+
and new_tag.strip()
|
|
502
|
+
):
|
|
503
|
+
if add_tag_to_source(source, new_tag.strip()):
|
|
504
|
+
st.success(f"Added tag: {new_tag}")
|
|
505
|
+
st.rerun()
|
|
506
|
+
else:
|
|
507
|
+
st.warning("Tag already exists")
|
|
504
508
|
|
|
505
509
|
# Check if this is a DOI/OpenAlex entry to show add buttons
|
|
506
510
|
doi = None
|
|
@@ -511,7 +515,7 @@ Adding: references, citations, and related works...
|
|
|
511
515
|
except Exception:
|
|
512
516
|
pass
|
|
513
517
|
|
|
514
|
-
if doi and (doi.startswith("http"
|
|
518
|
+
if doi and (doi.startswith(("http", "10."))):
|
|
515
519
|
st.markdown("---")
|
|
516
520
|
st.markdown("**Add Related Works:**")
|
|
517
521
|
col1, col2, col3 = st.columns(3)
|
|
@@ -642,7 +646,7 @@ Adding: references, citations, and related works...
|
|
|
642
646
|
except Exception:
|
|
643
647
|
pass
|
|
644
648
|
|
|
645
|
-
if doi and (doi.startswith("http"
|
|
649
|
+
if doi and (doi.startswith(("http", "10."))):
|
|
646
650
|
st.markdown("---")
|
|
647
651
|
st.markdown("**Add Related Works:**")
|
|
648
652
|
col1, col2, col3 = st.columns(3)
|
|
@@ -709,8 +713,8 @@ Adding: references, citations, and related works...
|
|
|
709
713
|
# Execute queries if needed
|
|
710
714
|
if should_run_query:
|
|
711
715
|
# Vector search
|
|
712
|
-
from sentence_transformers import SentenceTransformer
|
|
713
716
|
import numpy as np
|
|
717
|
+
from sentence_transformers import SentenceTransformer
|
|
714
718
|
|
|
715
719
|
config = get_config()
|
|
716
720
|
model = SentenceTransformer(config["embedding"]["model"])
|
|
@@ -794,7 +798,7 @@ Adding: references, citations, and related works...
|
|
|
794
798
|
except Exception:
|
|
795
799
|
pass
|
|
796
800
|
|
|
797
|
-
if doi and (doi.startswith("http"
|
|
801
|
+
if doi and (doi.startswith(("http", "10."))):
|
|
798
802
|
st.markdown("---")
|
|
799
803
|
st.markdown("**Add Related Works:**")
|
|
800
804
|
col1, col2, col3 = st.columns(3)
|
|
@@ -906,7 +910,7 @@ Adding: references, citations, and related works...
|
|
|
906
910
|
except Exception:
|
|
907
911
|
pass
|
|
908
912
|
|
|
909
|
-
if doi and (doi.startswith("http"
|
|
913
|
+
if doi and (doi.startswith(("http", "10."))):
|
|
910
914
|
st.markdown("---")
|
|
911
915
|
st.markdown("**Add Related Works:**")
|
|
912
916
|
col1, col2, col3 = st.columns(3)
|
|
@@ -1252,9 +1256,10 @@ def tab_semantic_scholar_search():
|
|
|
1252
1256
|
|
|
1253
1257
|
# Abstract
|
|
1254
1258
|
abstract = paper.get("abstract")
|
|
1255
|
-
if abstract
|
|
1256
|
-
|
|
1257
|
-
|
|
1259
|
+
if abstract and st.checkbox(
|
|
1260
|
+
"📄 Show Abstract", key=f"abstract_ss_{i}"
|
|
1261
|
+
):
|
|
1262
|
+
st.write(abstract)
|
|
1258
1263
|
|
|
1259
1264
|
# Add paper button
|
|
1260
1265
|
st.markdown("---")
|
|
@@ -1381,10 +1386,11 @@ def tab_suggest_reviewers():
|
|
|
1381
1386
|
|
|
1382
1387
|
try:
|
|
1383
1388
|
# Perform vector search to find similar papers
|
|
1384
|
-
from sentence_transformers import SentenceTransformer
|
|
1385
|
-
import numpy as np
|
|
1386
1389
|
from collections import Counter
|
|
1390
|
+
|
|
1391
|
+
import numpy as np
|
|
1387
1392
|
from more_itertools import batched
|
|
1393
|
+
from sentence_transformers import SentenceTransformer
|
|
1388
1394
|
|
|
1389
1395
|
config = get_config()
|
|
1390
1396
|
db = get_db()
|
|
@@ -1646,7 +1652,7 @@ def tab_add_content():
|
|
|
1646
1652
|
).fetchone()
|
|
1647
1653
|
|
|
1648
1654
|
if work_info:
|
|
1649
|
-
|
|
1655
|
+
_source, _text, extra = work_info
|
|
1650
1656
|
extra_data = json.loads(extra) if extra else {}
|
|
1651
1657
|
citation = format_citation(extra)
|
|
1652
1658
|
|
|
@@ -1669,7 +1675,7 @@ def tab_add_content():
|
|
|
1669
1675
|
|
|
1670
1676
|
except Exception as e:
|
|
1671
1677
|
failed_works.append({"doi": doi, "error": str(e)})
|
|
1672
|
-
status_text.error(f"✗ Failed {idx}/{len(dois)}: {
|
|
1678
|
+
status_text.error(f"✗ Failed {idx}/{len(dois)}: {e!s}")
|
|
1673
1679
|
|
|
1674
1680
|
progress_bar.progress(idx / len(dois))
|
|
1675
1681
|
|
|
@@ -1743,10 +1749,9 @@ def tab_add_content():
|
|
|
1743
1749
|
with cols[tag_idx]:
|
|
1744
1750
|
if st.button(
|
|
1745
1751
|
f"🗑️ {tag}", key=f"rm_tag_add_{idx}_{tag}"
|
|
1746
|
-
):
|
|
1747
|
-
|
|
1748
|
-
|
|
1749
|
-
st.rerun()
|
|
1752
|
+
) and remove_tag_from_source(work["doi"], tag):
|
|
1753
|
+
st.success(f"Removed tag: {tag}")
|
|
1754
|
+
st.rerun()
|
|
1750
1755
|
else:
|
|
1751
1756
|
st.caption("No tags yet")
|
|
1752
1757
|
|
|
@@ -1760,15 +1765,16 @@ def tab_add_content():
|
|
|
1760
1765
|
label_visibility="collapsed",
|
|
1761
1766
|
)
|
|
1762
1767
|
with new_tag_col2:
|
|
1763
|
-
if
|
|
1764
|
-
|
|
1765
|
-
|
|
1766
|
-
|
|
1767
|
-
|
|
1768
|
-
|
|
1769
|
-
|
|
1770
|
-
|
|
1771
|
-
|
|
1768
|
+
if (
|
|
1769
|
+
st.button("➕ Add", key=f"add_tag_btn_{idx}")
|
|
1770
|
+
and new_tag
|
|
1771
|
+
and new_tag.strip()
|
|
1772
|
+
):
|
|
1773
|
+
if add_tag_to_source(work["doi"], new_tag.strip()):
|
|
1774
|
+
st.success(f"Added tag: {new_tag}")
|
|
1775
|
+
st.rerun()
|
|
1776
|
+
else:
|
|
1777
|
+
st.warning("Tag already exists")
|
|
1772
1778
|
|
|
1773
1779
|
# Add Related Works buttons
|
|
1774
1780
|
st.markdown("---")
|
|
@@ -1874,8 +1880,10 @@ def tab_add_content():
|
|
|
1874
1880
|
|
|
1875
1881
|
if fromtext_submitted:
|
|
1876
1882
|
if text_input:
|
|
1877
|
-
import requests
|
|
1878
1883
|
from difflib import SequenceMatcher
|
|
1884
|
+
|
|
1885
|
+
import requests
|
|
1886
|
+
|
|
1879
1887
|
from litdb.chat import get_completion
|
|
1880
1888
|
|
|
1881
1889
|
with st.spinner("Extracting references using LLM..."):
|
|
@@ -2176,8 +2184,8 @@ Text:
|
|
|
2176
2184
|
file_submitted = st.form_submit_button("Add File")
|
|
2177
2185
|
|
|
2178
2186
|
if file_submitted and uploaded_file:
|
|
2179
|
-
import tempfile
|
|
2180
2187
|
import pathlib
|
|
2188
|
+
import tempfile
|
|
2181
2189
|
|
|
2182
2190
|
# Save uploaded file to temporary location
|
|
2183
2191
|
with tempfile.NamedTemporaryFile(
|
|
@@ -2189,9 +2197,10 @@ Text:
|
|
|
2189
2197
|
try:
|
|
2190
2198
|
with st.spinner(f"Processing {uploaded_file.name}..."):
|
|
2191
2199
|
# Import the add logic
|
|
2192
|
-
from litdb.commands.manage import add as cli_add
|
|
2193
2200
|
from click import Context
|
|
2194
2201
|
|
|
2202
|
+
from litdb.commands.manage import add as cli_add
|
|
2203
|
+
|
|
2195
2204
|
# Call the add function
|
|
2196
2205
|
with Context(cli_add) as ctx:
|
|
2197
2206
|
ctx.invoke(cli_add, sources=[tmp_path])
|
|
@@ -2222,9 +2231,10 @@ Text:
|
|
|
2222
2231
|
try:
|
|
2223
2232
|
with st.spinner(f"Processing {url_input}..."):
|
|
2224
2233
|
# Import the add logic
|
|
2225
|
-
from litdb.commands.manage import add as cli_add
|
|
2226
2234
|
from click import Context
|
|
2227
2235
|
|
|
2236
|
+
from litdb.commands.manage import add as cli_add
|
|
2237
|
+
|
|
2228
2238
|
# Call the add function
|
|
2229
2239
|
with Context(cli_add) as ctx:
|
|
2230
2240
|
ctx.invoke(cli_add, sources=[url_input])
|
|
@@ -2301,9 +2311,10 @@ Text:
|
|
|
2301
2311
|
successfully_added = []
|
|
2302
2312
|
failed_to_add = []
|
|
2303
2313
|
|
|
2304
|
-
from litdb.commands.manage import add as cli_add
|
|
2305
2314
|
from click import Context
|
|
2306
2315
|
|
|
2316
|
+
from litdb.commands.manage import add as cli_add
|
|
2317
|
+
|
|
2307
2318
|
for i, fname in enumerate(new_files):
|
|
2308
2319
|
status_text.text(
|
|
2309
2320
|
f"Adding {i + 1}/{len(new_files)}: {fname.name}"
|
|
@@ -2504,9 +2515,10 @@ def tab_manage_filters():
|
|
|
2504
2515
|
st.session_state.update_filters_clicked = False
|
|
2505
2516
|
|
|
2506
2517
|
# Import here where we actually use it
|
|
2507
|
-
from litdb.db import update_filter
|
|
2508
2518
|
import os
|
|
2509
2519
|
|
|
2520
|
+
from litdb.db import update_filter
|
|
2521
|
+
|
|
2510
2522
|
# Set offline mode to speed up embeddings
|
|
2511
2523
|
os.environ["TRANSFORMERS_OFFLINE"] = "1"
|
|
2512
2524
|
|
|
@@ -2553,11 +2565,9 @@ def tab_manage_filters():
|
|
|
2553
2565
|
status_text.info(f"✓ Filter {idx}/{len(filters)}: No new works")
|
|
2554
2566
|
|
|
2555
2567
|
except Exception as e:
|
|
2556
|
-
error_msg = f"Filter {idx}: {
|
|
2568
|
+
error_msg = f"Filter {idx}: {e!s}"
|
|
2557
2569
|
errors.append(error_msg)
|
|
2558
|
-
status_text.error(
|
|
2559
|
-
f"✗ Filter {idx}/{len(filters)}: Error - {str(e)}"
|
|
2560
|
-
)
|
|
2570
|
+
status_text.error(f"✗ Filter {idx}/{len(filters)}: Error - {e!s}")
|
|
2561
2571
|
|
|
2562
2572
|
progress_bar.progress(idx / len(filters))
|
|
2563
2573
|
|
|
@@ -2723,7 +2733,7 @@ def tab_manage_filters():
|
|
|
2723
2733
|
|
|
2724
2734
|
except Exception as e:
|
|
2725
2735
|
st.caption(
|
|
2726
|
-
f"Error formatting article {idx}: {
|
|
2736
|
+
f"Error formatting article {idx}: {e!s}"
|
|
2727
2737
|
)
|
|
2728
2738
|
else:
|
|
2729
2739
|
st.info(
|
|
@@ -2733,7 +2743,7 @@ def tab_manage_filters():
|
|
|
2733
2743
|
st.warning("Could not parse filter expression")
|
|
2734
2744
|
|
|
2735
2745
|
except Exception as e:
|
|
2736
|
-
st.error(f"Error loading articles: {
|
|
2746
|
+
st.error(f"Error loading articles: {e!s}")
|
|
2737
2747
|
|
|
2738
2748
|
st.markdown("---")
|
|
2739
2749
|
else:
|
|
@@ -3113,10 +3123,10 @@ focus the response and ask them what they would like.""",
|
|
|
3113
3123
|
st.session_state.research_step = "results"
|
|
3114
3124
|
st.rerun()
|
|
3115
3125
|
|
|
3116
|
-
except Exception
|
|
3126
|
+
except Exception:
|
|
3117
3127
|
status_placeholder.empty()
|
|
3118
3128
|
progress_bar.empty()
|
|
3119
|
-
raise
|
|
3129
|
+
raise
|
|
3120
3130
|
|
|
3121
3131
|
except ImportError:
|
|
3122
3132
|
st.error("Deep research requires gpt_researcher to be installed")
|
|
@@ -3262,8 +3272,9 @@ def tab_nsf_coa():
|
|
|
3262
3272
|
"Generating COA... This may take a few minutes depending on publication count."
|
|
3263
3273
|
):
|
|
3264
3274
|
try:
|
|
3265
|
-
import tempfile
|
|
3266
3275
|
import os
|
|
3276
|
+
import tempfile
|
|
3277
|
+
|
|
3267
3278
|
from litdb.coa import get_coa
|
|
3268
3279
|
|
|
3269
3280
|
# Create a temporary directory to store the file
|
|
@@ -1,10 +1,11 @@
|
|
|
1
1
|
"""Library for audio sources."""
|
|
2
2
|
|
|
3
|
-
import requests
|
|
4
|
-
from transformers import pipeline
|
|
5
3
|
import os
|
|
6
4
|
import tempfile
|
|
7
5
|
|
|
6
|
+
import requests
|
|
7
|
+
from transformers import pipeline
|
|
8
|
+
|
|
8
9
|
|
|
9
10
|
def is_audio_url(url):
|
|
10
11
|
"""Check if a given URL points to an audio file.
|
|
@@ -63,7 +64,7 @@ def get_audio_text(path):
|
|
|
63
64
|
except requests.exceptions.RequestException as e:
|
|
64
65
|
print(f"Error fetching audio from URL: {e}")
|
|
65
66
|
return None
|
|
66
|
-
except Exception as e:
|
|
67
|
+
except Exception as e: # noqa: BLE001 - whisper/ffmpeg raise many types
|
|
67
68
|
print(f"Error during transcription: {e}")
|
|
68
69
|
return None
|
|
69
70
|
|
|
@@ -73,9 +74,10 @@ def record():
|
|
|
73
74
|
|
|
74
75
|
Returns the audio filename it is recorded in.
|
|
75
76
|
"""
|
|
76
|
-
import pyaudio
|
|
77
|
-
import wave
|
|
78
77
|
import threading
|
|
78
|
+
import wave
|
|
79
|
+
|
|
80
|
+
import pyaudio
|
|
79
81
|
|
|
80
82
|
# Parameters for recording
|
|
81
83
|
FORMAT = pyaudio.paInt16
|
|
@@ -112,12 +114,11 @@ def record():
|
|
|
112
114
|
stream.close()
|
|
113
115
|
|
|
114
116
|
# Save the recorded data as a WAV file
|
|
115
|
-
|
|
116
|
-
|
|
117
|
-
|
|
118
|
-
|
|
119
|
-
|
|
120
|
-
wf.close()
|
|
117
|
+
with wave.open(audio_file, "wb") as wf:
|
|
118
|
+
wf.setnchannels(CHANNELS)
|
|
119
|
+
wf.setsampwidth(audio.get_sample_size(FORMAT))
|
|
120
|
+
wf.setframerate(RATE)
|
|
121
|
+
wf.writeframes(b"".join(frames))
|
|
121
122
|
print(" Done recording. Transcribing...")
|
|
122
123
|
|
|
123
124
|
# Event to signal when to stop recording
|
|
@@ -33,9 +33,9 @@ except ImportError:
|
|
|
33
33
|
full_jitter = None
|
|
34
34
|
|
|
35
35
|
|
|
36
|
-
from .
|
|
36
|
+
from .audio import get_audio_text, record
|
|
37
37
|
from .db import get_db
|
|
38
|
-
from .
|
|
38
|
+
from .utils import get_config
|
|
39
39
|
|
|
40
40
|
warnings.filterwarnings("ignore")
|
|
41
41
|
|
|
@@ -155,7 +155,9 @@ def expand_prompt(prompt):
|
|
|
155
155
|
pattern = r"(^<(.+)$)"
|
|
156
156
|
matches = re.findall(pattern, prompt, re.MULTILINE)
|
|
157
157
|
for _match, cmd in matches:
|
|
158
|
-
result = subprocess.run(
|
|
158
|
+
result = subprocess.run(
|
|
159
|
+
cmd.strip(), shell=True, text=True, capture_output=True, check=False
|
|
160
|
+
)
|
|
159
161
|
prompt = prompt.replace(_match, result.stdout)
|
|
160
162
|
|
|
161
163
|
return prompt
|
|
@@ -344,8 +346,10 @@ The following subcommands can be used:
|
|
|
344
346
|
|
|
345
347
|
elif prompt == "!save":
|
|
346
348
|
with open(input("Filename (chat.txt): ") or "chat.txt", "w") as f:
|
|
347
|
-
|
|
348
|
-
f
|
|
349
|
+
f.writelines(
|
|
350
|
+
f"{message['role']}: {message['content']}\n\n"
|
|
351
|
+
for message in messages
|
|
352
|
+
)
|
|
349
353
|
continue
|
|
350
354
|
|
|
351
355
|
elif prompt == "!restart":
|
|
@@ -3,29 +3,27 @@
|
|
|
3
3
|
The main command is litdb. There are subcommands for the actions.
|
|
4
4
|
"""
|
|
5
5
|
|
|
6
|
+
import logging
|
|
6
7
|
import warnings
|
|
7
8
|
|
|
8
9
|
import click
|
|
9
|
-
|
|
10
|
-
from .db import get_db
|
|
10
|
+
from transformers.utils import logging as tulogging
|
|
11
11
|
|
|
12
12
|
# Import command modules
|
|
13
13
|
from .commands import (
|
|
14
|
-
|
|
15
|
-
search,
|
|
14
|
+
data_processing,
|
|
16
15
|
export,
|
|
17
|
-
tags,
|
|
18
|
-
review,
|
|
19
16
|
filters,
|
|
17
|
+
install,
|
|
18
|
+
manage,
|
|
20
19
|
openalex_commands,
|
|
21
20
|
research_commands,
|
|
22
|
-
|
|
21
|
+
review,
|
|
22
|
+
search,
|
|
23
|
+
tags,
|
|
23
24
|
utilities,
|
|
24
|
-
install,
|
|
25
25
|
)
|
|
26
|
-
|
|
27
|
-
import logging
|
|
28
|
-
from transformers.utils import logging as tulogging
|
|
26
|
+
from .db import get_db
|
|
29
27
|
|
|
30
28
|
# Disable all Transformers logging
|
|
31
29
|
tulogging.set_verbosity_error()
|
|
@@ -49,7 +47,6 @@ except SystemExit:
|
|
|
49
47
|
@click.group()
|
|
50
48
|
def cli():
|
|
51
49
|
"""Group command for litdb."""
|
|
52
|
-
pass
|
|
53
50
|
|
|
54
51
|
|
|
55
52
|
# Register commands from manage module
|