Skip to content

Commit 91a3496

Browse files
SergiiShcherbakSergiiShcherbak
committed
Docs and README
1 parent 17053f3 commit 91a3496

File tree

2 files changed

+26
-116
lines changed

2 files changed

+26
-116
lines changed

‎README.md‎

Lines changed: 13 additions & 58 deletions
Original file line numberDiff line numberDiff line change
@@ -39,148 +39,103 @@ Read more on the project [motivation](https://contextgem.dev/motivation.html) in
3939
<tr>
4040
<td>⭐</td>
4141
<td>
42-
<strong>Automated dynamic prompts</strong><br>
43-
<i>
44-
Automatically generates comprehensive prompts for your specific extraction needs.
45-
</i>
42+
Automated dynamic prompts
4643
</td>
4744
<td>✅</td>
4845
<td>❌</td>
4946
</tr>
5047
<tr>
5148
<td>⭐</td>
5249
<td>
53-
<strong>Automated data modelling and validators</strong><br>
54-
<i>
55-
Automatically creates data models and validation logic.
56-
</i>
50+
Automated data modelling and validators
5751
</td>
5852
<td>✅</td>
5953
<td>❌</td>
6054
</tr>
6155
<tr>
6256
<td>⭐</td>
6357
<td>
64-
<strong>Single, unified extraction pipeline (declarative, reusable, fully serializable)</strong><br>
65-
<i>
66-
Allows to define a complete extraction workflow in a single, unified, reusable pipeline.
67-
</i>
58+
Single, unified extraction pipeline (declarative, reusable, fully serializable)
6859
</td>
6960
<td>✅</td>
7061
<td>❌</td>
7162
</tr>
7263
<tr>
7364
<td>⭐</td>
7465
<td>
75-
<strong>Precise granular reference mapping (paragraphs & sentences)</strong><br>
76-
<i>
77-
Automatically maps extracted data to the relevant parts of the document, which will always match
78-
in the source document, with customizable granularity.
79-
</i>
66+
Precise granular reference mapping (paragraphs & sentences)
8067
</td>
8168
<td>✅</td>
8269
<td>❌</td>
8370
</tr>
8471
<tr>
8572
<td>⭐</td>
8673
<td>
87-
<strong>Justifications (reasoning backing the extraction)</strong><br>
88-
<i>
89-
Automatically provides justifications for each extraction, with
90-
customizable granularity.
91-
</i>
74+
Justifications (reasoning backing the extraction)
9275
</td>
9376
<td>✅</td>
9477
<td>❌</td>
9578
</tr>
9679
<tr>
9780
<td>⭐</td>
9881
<td>
99-
<strong>Neural segmentation (SaT)</strong><br>
100-
<i>
101-
Automatically segments the document into paragraphs and sentences using state-of-the-art SaT
102-
models, compatible with many languages.
103-
</i>
82+
Neural segmentation (SaT)
10483
</td>
10584
<td>✅</td>
10685
<td>❌</td>
10786
</tr>
10887
<tr>
10988
<td>⭐</td>
11089
<td>
111-
<strong>Multilingual support (I/O without prompting)</strong><br>
112-
<i>
113-
Supports multiple languages in input and output without additional prompting.
114-
</i>
90+
Multilingual support (I/O without prompting)
11591
</td>
11692
<td>✅</td>
11793
<td>❌</td>
11894
</tr>
11995
<tr>
12096
<td>⭐</td>
12197
<td>
122-
<strong>Grouped LLMs with role-specific tasks</strong><br>
123-
<i>
124-
Allows to easily group LLMs with different roles to process role-specific
125-
tasks in the pipeline.
126-
</i>
98+
Grouped LLMs with role-specific tasks
12799
</td>
128100
<td>✅</td>
129101
<td>❌</td>
130102
</tr>
131103
<tr>
132104
<td>⭐</td>
133105
<td>
134-
<strong>Nested context extraction</strong><br>
135-
<i>
136-
Automatically manages nested context based on the pipeline definition (e.g.
137-
document > aspects > sub-aspects > concepts).
138-
</i>
106+
Nested context extraction
139107
</td>
140108
<td>✅</td>
141109
<td>⚠️</td>
142110
</tr>
143111
<tr>
144112
<td>⭐</td>
145113
<td>
146-
<strong>Built-in concurrent I/O processing</strong><br>
147-
<i>
148-
Automatically manages concurrent I/O processing to speed up complex
149-
extraction workflows, with a simple switch (<code>use_concurrency=True</code>).
150-
</i>
114+
Built-in concurrent I/O processing
151115
</td>
152116
<td>✅</td>
153117
<td>⚠️</td>
154118
</tr>
155119
<tr>
156120
<td>⭐</td>
157121
<td>
158-
<strong>Fallback and retry logic</strong><br>
159-
<i>
160-
Built-in retry logic and easily attachable fallback LLMs.
161-
</i>
122+
Fallback and retry logic
162123
</td>
163124
<td>✅</td>
164125
<td>✅</td>
165126
</tr>
166127
<tr>
167128
<td>⭐</td>
168129
<td>
169-
<strong>Multiple LLM providers</strong><br>
170-
<i>
171-
Compatible with a wide range of commercial and locally hosted LLMs.
172-
</i>
130+
Multiple LLM providers
173131
</td>
174132
<td>✅</td>
175133
<td>✅</td>
176134
</tr>
177135
<tr>
178136
<td>⭐</td>
179137
<td>
180-
<strong>Usage & costs tracking</strong><br>
181-
<i>
182-
Automatically tracks usage (calls, tokens, costs) of all LLM calls.
183-
</i>
138+
Usage & costs tracking
184139
</td>
185140
<td>✅</td>
186141
<td>✅</td>

‎dev/content_snippets/feature_table.html‎

Lines changed: 13 additions & 58 deletions
Original file line numberDiff line numberDiff line change
@@ -11,148 +11,103 @@
1111
<tr>
1212
<td>⭐</td>
1313
<td>
14-
<strong>Automated dynamic prompts</strong><br>
15-
<i>
16-
Automatically generates comprehensive prompts for your specific extraction needs.
17-
</i>
14+
Automated dynamic prompts
1815
</td>
1916
<td>✅</td>
2017
<td>❌</td>
2118
</tr>
2219
<tr>
2320
<td>⭐</td>
2421
<td>
25-
<strong>Automated data modelling and validators</strong><br>
26-
<i>
27-
Automatically creates data models and validation logic.
28-
</i>
22+
Automated data modelling and validators
2923
</td>
3024
<td>✅</td>
3125
<td>❌</td>
3226
</tr>
3327
<tr>
3428
<td>⭐</td>
3529
<td>
36-
<strong>Single, unified extraction pipeline (declarative, reusable, fully serializable)</strong><br>
37-
<i>
38-
Allows to define a complete extraction workflow in a single, unified, reusable pipeline.
39-
</i>
30+
Single, unified extraction pipeline (declarative, reusable, fully serializable)
4031
</td>
4132
<td>✅</td>
4233
<td>❌</td>
4334
</tr>
4435
<tr>
4536
<td>⭐</td>
4637
<td>
47-
<strong>Precise granular reference mapping (paragraphs & sentences)</strong><br>
48-
<i>
49-
Automatically maps extracted data to the relevant parts of the document, which will always match
50-
in the source document, with customizable granularity.
51-
</i>
38+
Precise granular reference mapping (paragraphs & sentences)
5239
</td>
5340
<td>✅</td>
5441
<td>❌</td>
5542
</tr>
5643
<tr>
5744
<td>⭐</td>
5845
<td>
59-
<strong>Justifications (reasoning backing the extraction)</strong><br>
60-
<i>
61-
Automatically provides justifications for each extraction, with
62-
customizable granularity.
63-
</i>
46+
Justifications (reasoning backing the extraction)
6447
</td>
6548
<td>✅</td>
6649
<td>❌</td>
6750
</tr>
6851
<tr>
6952
<td>⭐</td>
7053
<td>
71-
<strong>Neural segmentation (SaT)</strong><br>
72-
<i>
73-
Automatically segments the document into paragraphs and sentences using state-of-the-art SaT
74-
models, compatible with many languages.
75-
</i>
54+
Neural segmentation (SaT)
7655
</td>
7756
<td>✅</td>
7857
<td>❌</td>
7958
</tr>
8059
<tr>
8160
<td>⭐</td>
8261
<td>
83-
<strong>Multilingual support (I/O without prompting)</strong><br>
84-
<i>
85-
Supports multiple languages in input and output without additional prompting.
86-
</i>
62+
Multilingual support (I/O without prompting)
8763
</td>
8864
<td>✅</td>
8965
<td>❌</td>
9066
</tr>
9167
<tr>
9268
<td>⭐</td>
9369
<td>
94-
<strong>Grouped LLMs with role-specific tasks</strong><br>
95-
<i>
96-
Allows to easily group LLMs with different roles to process role-specific
97-
tasks in the pipeline.
98-
</i>
70+
Grouped LLMs with role-specific tasks
9971
</td>
10072
<td>✅</td>
10173
<td>❌</td>
10274
</tr>
10375
<tr>
10476
<td>⭐</td>
10577
<td>
106-
<strong>Nested context extraction</strong><br>
107-
<i>
108-
Automatically manages nested context based on the pipeline definition (e.g.
109-
document > aspects > sub-aspects > concepts).
110-
</i>
78+
Nested context extraction
11179
</td>
11280
<td>✅</td>
11381
<td>⚠️</td>
11482
</tr>
11583
<tr>
11684
<td>⭐</td>
11785
<td>
118-
<strong>Built-in concurrent I/O processing</strong><br>
119-
<i>
120-
Automatically manages concurrent I/O processing to speed up complex
121-
extraction workflows, with a simple switch (<code>use_concurrency=True</code>).
122-
</i>
86+
Built-in concurrent I/O processing
12387
</td>
12488
<td>✅</td>
12589
<td>⚠️</td>
12690
</tr>
12791
<tr>
12892
<td>⭐</td>
12993
<td>
130-
<strong>Fallback and retry logic</strong><br>
131-
<i>
132-
Built-in retry logic and easily attachable fallback LLMs.
133-
</i>
94+
Fallback and retry logic
13495
</td>
13596
<td>✅</td>
13697
<td>✅</td>
13798
</tr>
13899
<tr>
139100
<td>⭐</td>
140101
<td>
141-
<strong>Multiple LLM providers</strong><br>
142-
<i>
143-
Compatible with a wide range of commercial and locally hosted LLMs.
144-
</i>
102+
Multiple LLM providers
145103
</td>
146104
<td>✅</td>
147105
<td>✅</td>
148106
</tr>
149107
<tr>
150108
<td>⭐</td>
151109
<td>
152-
<strong>Usage & costs tracking</strong><br>
153-
<i>
154-
Automatically tracks usage (calls, tokens, costs) of all LLM calls.
155-
</i>
110+
Usage & costs tracking
156111
</td>
157112
<td>✅</td>
158113
<td>✅</td>

0 commit comments

Comments
 (0)