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
|
plugin_register functions/language_model
[[0,0.0,0.0],true]
plugin_register functions/vector
[[0,0.0,0.0],true]
table_create Data TABLE_NO_KEY
[[0,0.0,0.0],true]
column_create Data text COLUMN_SCALAR ShortText
[[0,0.0,0.0],true]
load --table Data
[
{"text": "I am a king."},
{"text": "I am a queen."}
]
[[0,0.0,0.0],2]
select Data --columns[embeddings].stage output --columns[embeddings].type Float32 --columns[embeddings].flags COLUMN_VECTOR --columns[embeddings].value 'language_model_vectorize("hf:///groonga/multilingual-e5-base-Q4_K_M-GGUF", "passage: " + text)' --output_columns 'text, vector_size(embeddings)'
[
[
0,
0.0,
0.0
],
[
[
[
2
],
[
[
"text",
"ShortText"
],
[
"vector_size",
null
]
],
[
"I am a king.",
768
],
[
"I am a queen.",
768
]
]
]
]
#|w| load: model vocab missing newline token, using special_pad_id instead
#|w| load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
|
