1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
|
{
lib,
buildPythonPackage,
fetchFromGitHub,
# build-system
setuptools,
# dependencies
faiss,
torch,
transformers,
huggingface-hub,
numpy,
pyyaml,
regex,
# optional-dependencies
# agent
mcpadapt,
smolagents,
# ann
annoy,
hnswlib,
pgvector,
sqlalchemy,
sqlite-vec-c,
# api
aiohttp,
fastapi,
fastapi-mcp,
httpx,
pillow,
python-multipart,
uvicorn,
# cloud
# apache-libcloud, (unpackaged)
fasteners,
# console
rich,
# database
duckdb,
# graph
# grand-cypher (unpackaged)
# grand-graph (unpackaged)
networkx,
# model
onnx,
onnxruntime,
# pipeline-audio
# model2vec,
sounddevice,
soundfile,
scipy,
ttstokenizer,
webrtcvad,
# pipeline-data
beautifulsoup4,
nltk,
pandas,
tika,
# pipeline-image
imagehash,
timm,
# pipeline-llm
litellm,
# llama-cpp-python, (unpackaged)
# pipeline-text
gliner,
sentencepiece,
staticvectors,
# pipeline-train
accelerate,
bitsandbytes,
onnxmltools,
peft,
skl2onnx,
# vectors
fasttext,
# pymagnitude-lite, (unpackaged)
scikit-learn,
sentence-transformers,
skops,
# workflow
# apache-libcloud (unpackaged)
croniter,
openpyxl,
requests,
xmltodict,
# tests
msgpack,
pytestCheckHook,
}:
let
version = "9.3.0";
agent = [
mcpadapt
smolagents
];
ann = [
annoy
hnswlib
pgvector
sqlalchemy
sqlite-vec-c
];
api = [
aiohttp
fastapi
fastapi-mcp
httpx
pillow
python-multipart
uvicorn
];
cloud = [
# apache-libcloud
fasteners
];
console = [ rich ];
database = [
duckdb
pillow
sqlalchemy
];
graph = [
# grand-cypher
# grand-graph
networkx
sqlalchemy
];
model = [
onnx
onnxruntime
];
pipeline-audio = [
onnx
onnxruntime
scipy
sounddevice
soundfile
ttstokenizer
webrtcvad
];
pipeline-data = [
beautifulsoup4
nltk
pandas
tika
];
pipeline-image = [
imagehash
pillow
timm
];
pipeline-llm = [
litellm
# llama-cpp-python
];
pipeline-text = [
gliner
sentencepiece
staticvectors
];
pipeline-train = [
accelerate
bitsandbytes
onnx
onnxmltools
onnxruntime
peft
skl2onnx
];
pipeline =
pipeline-audio
++ pipeline-data
++ pipeline-image
++ pipeline-llm
++ pipeline-text
++ pipeline-train;
scoring = [ sqlalchemy ];
vectors = [
fasttext
litellm
# llama-cpp-python
# model2vec
# pymagnitude-lite
scikit-learn
sentence-transformers
skops
];
workflow = [
# apache-libcloud
croniter
openpyxl
pandas
pillow
requests
xmltodict
];
similarity = ann ++ vectors;
all =
agent
++ api
++ ann
++ console
++ database
++ graph
++ model
++ pipeline
++ scoring
++ similarity
++ workflow;
optional-dependencies = {
inherit
agent
ann
api
cloud
console
database
graph
model
pipeline-audio
pipeline-data
pipeline-image
pipeline-llm
pipeline-text
pipeline-train
pipeline
scoring
similarity
workflow
all
;
};
src = fetchFromGitHub {
owner = "neuml";
repo = "txtai";
tag = "v${version}";
hash = "sha256-dKZiyExKAIO1fEQSkmkTX0eqKgsKSurZWFWkeeiOBIE=";
};
in
buildPythonPackage {
pname = "txtai";
inherit version src;
pyproject = true;
build-system = [ setuptools ];
pythonRemoveDeps = [
# We call it faiss, not faiss-cpu.
"faiss-cpu"
];
dependencies = [
faiss
huggingface-hub
msgpack
numpy
pyyaml
regex
torch
transformers
];
optional-dependencies = optional-dependencies;
# The Python imports check runs huggingface-hub which needs a writable directory.
# `pythonImportsCheck` runs in the installPhase (before checkPhase).
preInstall = ''
export HF_HOME=$(mktemp -d)
'';
pythonImportsCheck = [ "txtai" ];
nativeCheckInputs = [
httpx
msgpack
pytestCheckHook
python-multipart
timm
sqlalchemy
]
++ optional-dependencies.agent
++ optional-dependencies.ann
++ optional-dependencies.api
++ optional-dependencies.similarity;
pytestFlagsArray = [
"test/python/*"
];
disabledTests = [
# Hardcoded paths
"testInvalidTar"
"testInvalidZip"
# Downloads from Huggingface
"TestAgent"
"TestCloud"
"TestConsole"
"TestEmbeddings"
"TestGraph"
"TestWorkflow"
"testPipeline"
"testVectors"
# Not finding sqlite-vec despite being supplied
"testSQLite"
"testSQLiteCustom"
];
meta = {
description = "Semantic search and workflows powered by language models";
changelog = "https://github.com/neuml/txtai/releases/tag/${src.tag}";
homepage = "https://github.com/neuml/txtai";
license = lib.licenses.asl20;
maintainers = with lib.maintainers; [ happysalada ];
};
}
|
