Spaces:
Running
Running
RabotiahovDmytro
commited on
Commit
•
4c65e87
1
Parent(s):
172d9b6
Upload 14 files
Browse files- .env +4 -0
- .gitignore +162 -0
- .python-version +1 -0
- LICENSE +201 -0
- RAG_project_plan.txt +11 -0
- README.md +1 -12
- chatbot/__init__.py +0 -0
- chatbot/bot.py +69 -0
- chatbot/retriever.py +132 -0
- data/CountMonteCristoFull.txt +0 -0
- data/chunked_data_corpus.csv +0 -0
- data/prepare_data.py +66 -0
- main.py +31 -0
- requirements.txt +0 -0
.env
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
GROQ_API_KEY=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
|
2 |
+
DENSE_RETRIEVER_MODEL_NAME = all-MiniLM-L6-v2
|
3 |
+
CROSS_ENCODER_MODEL_NAME = cross-encoder/ms-marco-MiniLM-L-12-v2
|
4 |
+
LLM_CORE_MODEL_NAME = groq/llama3-8b-8192
|
.gitignore
ADDED
@@ -0,0 +1,162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Byte-compiled / optimized / DLL files
|
2 |
+
__pycache__/
|
3 |
+
*.py[cod]
|
4 |
+
*$py.class
|
5 |
+
|
6 |
+
# C extensions
|
7 |
+
*.so
|
8 |
+
|
9 |
+
# Distribution / packaging
|
10 |
+
.Python
|
11 |
+
build/
|
12 |
+
develop-eggs/
|
13 |
+
dist/
|
14 |
+
downloads/
|
15 |
+
eggs/
|
16 |
+
.eggs/
|
17 |
+
lib/
|
18 |
+
lib64/
|
19 |
+
parts/
|
20 |
+
sdist/
|
21 |
+
var/
|
22 |
+
wheels/
|
23 |
+
share/python-wheels/
|
24 |
+
*.egg-info/
|
25 |
+
.installed.cfg
|
26 |
+
*.egg
|
27 |
+
MANIFEST
|
28 |
+
|
29 |
+
# PyInstaller
|
30 |
+
# Usually these files are written by a python script from a template
|
31 |
+
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
32 |
+
*.manifest
|
33 |
+
*.spec
|
34 |
+
|
35 |
+
# Installer logs
|
36 |
+
pip-log.txt
|
37 |
+
pip-delete-this-directory.txt
|
38 |
+
|
39 |
+
# Unit test / coverage reports
|
40 |
+
htmlcov/
|
41 |
+
.tox/
|
42 |
+
.nox/
|
43 |
+
.coverage
|
44 |
+
.coverage.*
|
45 |
+
.cache
|
46 |
+
nosetests.xml
|
47 |
+
coverage.xml
|
48 |
+
*.cover
|
49 |
+
*.py,cover
|
50 |
+
.hypothesis/
|
51 |
+
.pytest_cache/
|
52 |
+
cover/
|
53 |
+
|
54 |
+
# Translations
|
55 |
+
*.mo
|
56 |
+
*.pot
|
57 |
+
|
58 |
+
# Django stuff:
|
59 |
+
*.log
|
60 |
+
local_settings.py
|
61 |
+
db.sqlite3
|
62 |
+
db.sqlite3-journal
|
63 |
+
|
64 |
+
# Flask stuff:
|
65 |
+
instance/
|
66 |
+
.webassets-cache
|
67 |
+
|
68 |
+
# Scrapy stuff:
|
69 |
+
.scrapy
|
70 |
+
|
71 |
+
# Sphinx documentation
|
72 |
+
docs/_build/
|
73 |
+
|
74 |
+
# PyBuilder
|
75 |
+
.pybuilder/
|
76 |
+
target/
|
77 |
+
|
78 |
+
# Jupyter Notebook
|
79 |
+
.ipynb_checkpoints
|
80 |
+
|
81 |
+
# IPython
|
82 |
+
profile_default/
|
83 |
+
ipython_config.py
|
84 |
+
|
85 |
+
# pyenv
|
86 |
+
# For a library or package, you might want to ignore these files since the code is
|
87 |
+
# intended to run in multiple environments; otherwise, check them in:
|
88 |
+
.python-version
|
89 |
+
|
90 |
+
# pipenv
|
91 |
+
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
92 |
+
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
93 |
+
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
94 |
+
# install all needed dependencies.
|
95 |
+
#Pipfile.lock
|
96 |
+
|
97 |
+
# poetry
|
98 |
+
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
99 |
+
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
100 |
+
# commonly ignored for libraries.
|
101 |
+
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
102 |
+
#poetry.lock
|
103 |
+
|
104 |
+
# pdm
|
105 |
+
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
106 |
+
#pdm.lock
|
107 |
+
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
|
108 |
+
# in version control.
|
109 |
+
# https://pdm.fming.dev/latest/usage/project/#working-with-version-control
|
110 |
+
.pdm.toml
|
111 |
+
.pdm-python
|
112 |
+
.pdm-build/
|
113 |
+
|
114 |
+
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
115 |
+
__pypackages__/
|
116 |
+
|
117 |
+
# Celery stuff
|
118 |
+
celerybeat-schedule
|
119 |
+
celerybeat.pid
|
120 |
+
|
121 |
+
# SageMath parsed files
|
122 |
+
*.sage.py
|
123 |
+
|
124 |
+
# Environments
|
125 |
+
.env
|
126 |
+
.venv
|
127 |
+
env/
|
128 |
+
venv/
|
129 |
+
ENV/
|
130 |
+
env.bak/
|
131 |
+
venv.bak/
|
132 |
+
|
133 |
+
# Spyder project settings
|
134 |
+
.spyderproject
|
135 |
+
.spyproject
|
136 |
+
|
137 |
+
# Rope project settings
|
138 |
+
.ropeproject
|
139 |
+
|
140 |
+
# mkdocs documentation
|
141 |
+
/site
|
142 |
+
|
143 |
+
# mypy
|
144 |
+
.mypy_cache/
|
145 |
+
.dmypy.json
|
146 |
+
dmypy.json
|
147 |
+
|
148 |
+
# Pyre type checker
|
149 |
+
.pyre/
|
150 |
+
|
151 |
+
# pytype static type analyzer
|
152 |
+
.pytype/
|
153 |
+
|
154 |
+
# Cython debug symbols
|
155 |
+
cython_debug/
|
156 |
+
|
157 |
+
# PyCharm
|
158 |
+
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
159 |
+
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
160 |
+
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
161 |
+
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
162 |
+
#.idea/
|
.python-version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
3.10.2
|
LICENSE
ADDED
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Apache License
|
2 |
+
Version 2.0, January 2004
|
3 |
+
http://www.apache.org/licenses/
|
4 |
+
|
5 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
6 |
+
|
7 |
+
1. Definitions.
|
8 |
+
|
9 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
10 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
11 |
+
|
12 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
13 |
+
the copyright owner that is granting the License.
|
14 |
+
|
15 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
16 |
+
other entities that control, are controlled by, or are under common
|
17 |
+
control with that entity. For the purposes of this definition,
|
18 |
+
"control" means (i) the power, direct or indirect, to cause the
|
19 |
+
direction or management of such entity, whether by contract or
|
20 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
21 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
22 |
+
|
23 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
24 |
+
exercising permissions granted by this License.
|
25 |
+
|
26 |
+
"Source" form shall mean the preferred form for making modifications,
|
27 |
+
including but not limited to software source code, documentation
|
28 |
+
source, and configuration files.
|
29 |
+
|
30 |
+
"Object" form shall mean any form resulting from mechanical
|
31 |
+
transformation or translation of a Source form, including but
|
32 |
+
not limited to compiled object code, generated documentation,
|
33 |
+
and conversions to other media types.
|
34 |
+
|
35 |
+
"Work" shall mean the work of authorship, whether in Source or
|
36 |
+
Object form, made available under the License, as indicated by a
|
37 |
+
copyright notice that is included in or attached to the work
|
38 |
+
(an example is provided in the Appendix below).
|
39 |
+
|
40 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
41 |
+
form, that is based on (or derived from) the Work and for which the
|
42 |
+
editorial revisions, annotations, elaborations, or other modifications
|
43 |
+
represent, as a whole, an original work of authorship. For the purposes
|
44 |
+
of this License, Derivative Works shall not include works that remain
|
45 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
46 |
+
the Work and Derivative Works thereof.
|
47 |
+
|
48 |
+
"Contribution" shall mean any work of authorship, including
|
49 |
+
the original version of the Work and any modifications or additions
|
50 |
+
to that Work or Derivative Works thereof, that is intentionally
|
51 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
52 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
53 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
54 |
+
means any form of electronic, verbal, or written communication sent
|
55 |
+
to the Licensor or its representatives, including but not limited to
|
56 |
+
communication on electronic mailing lists, source code control systems,
|
57 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
58 |
+
Licensor for the purpose of discussing and improving the Work, but
|
59 |
+
excluding communication that is conspicuously marked or otherwise
|
60 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
61 |
+
|
62 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
63 |
+
on behalf of whom a Contribution has been received by Licensor and
|
64 |
+
subsequently incorporated within the Work.
|
65 |
+
|
66 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
67 |
+
this License, each Contributor hereby grants to You a perpetual,
|
68 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
69 |
+
copyright license to reproduce, prepare Derivative Works of,
|
70 |
+
publicly display, publicly perform, sublicense, and distribute the
|
71 |
+
Work and such Derivative Works in Source or Object form.
|
72 |
+
|
73 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
74 |
+
this License, each Contributor hereby grants to You a perpetual,
|
75 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
76 |
+
(except as stated in this section) patent license to make, have made,
|
77 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
78 |
+
where such license applies only to those patent claims licensable
|
79 |
+
by such Contributor that are necessarily infringed by their
|
80 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
81 |
+
with the Work to which such Contribution(s) was submitted. If You
|
82 |
+
institute patent litigation against any entity (including a
|
83 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
84 |
+
or a Contribution incorporated within the Work constitutes direct
|
85 |
+
or contributory patent infringement, then any patent licenses
|
86 |
+
granted to You under this License for that Work shall terminate
|
87 |
+
as of the date such litigation is filed.
|
88 |
+
|
89 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
90 |
+
Work or Derivative Works thereof in any medium, with or without
|
91 |
+
modifications, and in Source or Object form, provided that You
|
92 |
+
meet the following conditions:
|
93 |
+
|
94 |
+
(a) You must give any other recipients of the Work or
|
95 |
+
Derivative Works a copy of this License; and
|
96 |
+
|
97 |
+
(b) You must cause any modified files to carry prominent notices
|
98 |
+
stating that You changed the files; and
|
99 |
+
|
100 |
+
(c) You must retain, in the Source form of any Derivative Works
|
101 |
+
that You distribute, all copyright, patent, trademark, and
|
102 |
+
attribution notices from the Source form of the Work,
|
103 |
+
excluding those notices that do not pertain to any part of
|
104 |
+
the Derivative Works; and
|
105 |
+
|
106 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
107 |
+
distribution, then any Derivative Works that You distribute must
|
108 |
+
include a readable copy of the attribution notices contained
|
109 |
+
within such NOTICE file, excluding those notices that do not
|
110 |
+
pertain to any part of the Derivative Works, in at least one
|
111 |
+
of the following places: within a NOTICE text file distributed
|
112 |
+
as part of the Derivative Works; within the Source form or
|
113 |
+
documentation, if provided along with the Derivative Works; or,
|
114 |
+
within a display generated by the Derivative Works, if and
|
115 |
+
wherever such third-party notices normally appear. The contents
|
116 |
+
of the NOTICE file are for informational purposes only and
|
117 |
+
do not modify the License. You may add Your own attribution
|
118 |
+
notices within Derivative Works that You distribute, alongside
|
119 |
+
or as an addendum to the NOTICE text from the Work, provided
|
120 |
+
that such additional attribution notices cannot be construed
|
121 |
+
as modifying the License.
|
122 |
+
|
123 |
+
You may add Your own copyright statement to Your modifications and
|
124 |
+
may provide additional or different license terms and conditions
|
125 |
+
for use, reproduction, or distribution of Your modifications, or
|
126 |
+
for any such Derivative Works as a whole, provided Your use,
|
127 |
+
reproduction, and distribution of the Work otherwise complies with
|
128 |
+
the conditions stated in this License.
|
129 |
+
|
130 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
131 |
+
any Contribution intentionally submitted for inclusion in the Work
|
132 |
+
by You to the Licensor shall be under the terms and conditions of
|
133 |
+
this License, without any additional terms or conditions.
|
134 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
135 |
+
the terms of any separate license agreement you may have executed
|
136 |
+
with Licensor regarding such Contributions.
|
137 |
+
|
138 |
+
6. Trademarks. This License does not grant permission to use the trade
|
139 |
+
names, trademarks, service marks, or product names of the Licensor,
|
140 |
+
except as required for reasonable and customary use in describing the
|
141 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
142 |
+
|
143 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
144 |
+
agreed to in writing, Licensor provides the Work (and each
|
145 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
146 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
147 |
+
implied, including, without limitation, any warranties or conditions
|
148 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
149 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
150 |
+
appropriateness of using or redistributing the Work and assume any
|
151 |
+
risks associated with Your exercise of permissions under this License.
|
152 |
+
|
153 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
154 |
+
whether in tort (including negligence), contract, or otherwise,
|
155 |
+
unless required by applicable law (such as deliberate and grossly
|
156 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
157 |
+
liable to You for damages, including any direct, indirect, special,
|
158 |
+
incidental, or consequential damages of any character arising as a
|
159 |
+
result of this License or out of the use or inability to use the
|
160 |
+
Work (including but not limited to damages for loss of goodwill,
|
161 |
+
work stoppage, computer failure or malfunction, or any and all
|
162 |
+
other commercial damages or losses), even if such Contributor
|
163 |
+
has been advised of the possibility of such damages.
|
164 |
+
|
165 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
166 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
167 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
168 |
+
or other liability obligations and/or rights consistent with this
|
169 |
+
License. However, in accepting such obligations, You may act only
|
170 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
171 |
+
of any other Contributor, and only if You agree to indemnify,
|
172 |
+
defend, and hold each Contributor harmless for any liability
|
173 |
+
incurred by, or claims asserted against, such Contributor by reason
|
174 |
+
of your accepting any such warranty or additional liability.
|
175 |
+
|
176 |
+
END OF TERMS AND CONDITIONS
|
177 |
+
|
178 |
+
APPENDIX: How to apply the Apache License to your work.
|
179 |
+
|
180 |
+
To apply the Apache License to your work, attach the following
|
181 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
182 |
+
replaced with your own identifying information. (Don't include
|
183 |
+
the brackets!) The text should be enclosed in the appropriate
|
184 |
+
comment syntax for the file format. We also recommend that a
|
185 |
+
file or class name and description of purpose be included on the
|
186 |
+
same "printed page" as the copyright notice for easier
|
187 |
+
identification within third-party archives.
|
188 |
+
|
189 |
+
Copyright [yyyy] [name of copyright owner]
|
190 |
+
|
191 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
192 |
+
you may not use this file except in compliance with the License.
|
193 |
+
You may obtain a copy of the License at
|
194 |
+
|
195 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
196 |
+
|
197 |
+
Unless required by applicable law or agreed to in writing, software
|
198 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
199 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
200 |
+
See the License for the specific language governing permissions and
|
201 |
+
limitations under the License.
|
RAG_project_plan.txt
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
RAG project planning:
|
2 |
+
1. Data source: book(full english version of Count of Monte Cristo).
|
3 |
+
2. Chunking done by size.
|
4 |
+
3. Retriver bm25 + bi-encoder.
|
5 |
+
4. Reranker(sentence bert).
|
6 |
+
5. LiteLLM library (llama3-8b-8192 model).
|
7 |
+
6. Metadata filtering wasn't used.
|
8 |
+
7. Citation: user will be provided with the text citation along with Chapter this text belongs to.
|
9 |
+
8. Vector database wasn't used.
|
10 |
+
9. Web UI done with gradio
|
11 |
+
|
README.md
CHANGED
@@ -1,12 +1 @@
|
|
1 |
-
|
2 |
-
title: RAGSystem
|
3 |
-
emoji: 🐠
|
4 |
-
colorFrom: indigo
|
5 |
-
colorTo: green
|
6 |
-
sdk: docker
|
7 |
-
pinned: false
|
8 |
-
license: apache-2.0
|
9 |
-
short_description: RAG system based on the book 'The Count of Monte Cristo'
|
10 |
-
---
|
11 |
-
|
12 |
-
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
1 |
+
# Neural_Networks_RAG
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
chatbot/__init__.py
ADDED
File without changes
|
chatbot/bot.py
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from chatbot.retriever import HybridRetrieverReranker
|
2 |
+
from litellm import completion
|
3 |
+
import os
|
4 |
+
import ast
|
5 |
+
|
6 |
+
GROQ_API_KEY = os.getenv("GROQ_API_KEY")
|
7 |
+
DENSE_RETRIEVER_MODEL_NAME = "all-MiniLM-L6-v2"
|
8 |
+
CROSS_ENCODER_MODEL_NAME = "cross-encoder/ms-marco-MiniLM-L-12-v2"
|
9 |
+
LLM_CORE_MODEL_NAME = "groq/llama3-8b-8192"
|
10 |
+
|
11 |
+
|
12 |
+
class QuestionAnsweringBot:
|
13 |
+
|
14 |
+
def __init__(self, docs, enable_bm25=True, enable_dense=True, enable_rerank=True, top_k_bm25=60, top_n_dense=30, top_n_rerank=2) -> None:
|
15 |
+
self.retriever = HybridRetrieverReranker(docs)
|
16 |
+
self.enable_bm25 = enable_bm25
|
17 |
+
self.enable_dense = enable_dense
|
18 |
+
self.enable_rerank = enable_rerank
|
19 |
+
self.top_k_bm25=top_k_bm25
|
20 |
+
self.top_n_dense=top_n_dense
|
21 |
+
self.top_n_rerank=top_n_rerank
|
22 |
+
|
23 |
+
def __get_answer__(self, question: str) -> str:
|
24 |
+
PROMPT = """\
|
25 |
+
You are an intelligent assistant designed to provide accurate and relevant answers based on the provided context.
|
26 |
+
|
27 |
+
Rules:
|
28 |
+
- Always analyze the provided context thoroughly before answering.
|
29 |
+
- Respond with factual and concise information.
|
30 |
+
- If context is ambiguous or insufficient or you can't find answer, say 'I don't know.'
|
31 |
+
- Do not speculate or fabricate information beyond the provided context.
|
32 |
+
- Follow user instructions on the response style(default style is detailed response if user didn't provide any specifications):
|
33 |
+
- If the user asks for a detailed response, provide comprehensive explanations.
|
34 |
+
- If the user requests brevity, give concise and to-the-point answers.
|
35 |
+
- When applicable, summarize and synthesize information from the context to answer effectively.
|
36 |
+
- Avoid using information outside the given context.
|
37 |
+
"""
|
38 |
+
context = self.retriever.hybrid_retrieve(question,
|
39 |
+
enable_bm25=self.enable_bm25,
|
40 |
+
enable_dense=self.enable_dense,
|
41 |
+
enable_rerank=self.enable_rerank,
|
42 |
+
top_k_bm25=self.top_k_bm25,
|
43 |
+
top_n_dense=self.top_n_dense,
|
44 |
+
top_n_rerank=self.top_n_rerank
|
45 |
+
)
|
46 |
+
|
47 |
+
context_text = [doc['raw_text'] for doc in context]
|
48 |
+
|
49 |
+
response = completion(
|
50 |
+
model=LLM_CORE_MODEL_NAME,
|
51 |
+
temperature=0.0,
|
52 |
+
messages=[
|
53 |
+
{"role": "system", "content": PROMPT},
|
54 |
+
{"role": "user", "content": f"Context: {context_text}\nQuestion: {question}"}
|
55 |
+
],
|
56 |
+
api_key=GROQ_API_KEY
|
57 |
+
)
|
58 |
+
return response, context
|
59 |
+
|
60 |
+
def form_response(self, question):
|
61 |
+
llm_response, context = self.__get_answer__(question)
|
62 |
+
|
63 |
+
metadata_raw = [doc['chapter_name'] for doc in context]
|
64 |
+
metadata_cleaned = [ast.literal_eval(item) for item in metadata_raw]
|
65 |
+
|
66 |
+
print('User:', question)
|
67 |
+
print('System:', llm_response.choices[0].message.content)
|
68 |
+
|
69 |
+
return f"**{llm_response.choices[0].message.content}**\n\nResources: {[chapter for doc in metadata_cleaned for chapter in doc]}"
|
chatbot/retriever.py
ADDED
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from rank_bm25 import BM25Okapi
|
2 |
+
import numpy as np
|
3 |
+
import torch
|
4 |
+
import re
|
5 |
+
import string
|
6 |
+
from sentence_transformers import SentenceTransformer, util, CrossEncoder
|
7 |
+
|
8 |
+
|
9 |
+
DENSE_RETRIEVER_MODEL_NAME = "all-MiniLM-L6-v2"
|
10 |
+
CROSS_ENCODER_MODEL_NAME = 'cross-encoder/ms-marco-MiniLM-L-12-v2'
|
11 |
+
LLM_CORE_MODEL_NAME = "groq/llama3-8b-8192"
|
12 |
+
|
13 |
+
|
14 |
+
def clean_text(text):
|
15 |
+
text = text.translate(str.maketrans('', '', string.punctuation))
|
16 |
+
text = text.lower()
|
17 |
+
text = re.sub(r'[^a-zA-Z0-9\s]', '', text)
|
18 |
+
text = re.sub(r'\s+', ' ', text)
|
19 |
+
|
20 |
+
return text.strip()
|
21 |
+
|
22 |
+
|
23 |
+
class HybridRetrieverReranker:
|
24 |
+
def __init__(self, dataset, dense_model_name=DENSE_RETRIEVER_MODEL_NAME, cross_encoder_model=CROSS_ENCODER_MODEL_NAME):
|
25 |
+
if 'cleaned_text' not in dataset.columns:
|
26 |
+
raise ValueError("Dataset must contain a 'cleaned_text' column.")
|
27 |
+
|
28 |
+
self.dataset = dataset
|
29 |
+
self.bm25_corpus = dataset['cleaned_text'].tolist()
|
30 |
+
self.tokenized_corpus = [chunk.split() for chunk in self.bm25_corpus]
|
31 |
+
self.bm25 = BM25Okapi(self.tokenized_corpus)
|
32 |
+
|
33 |
+
self.dense_model = SentenceTransformer(dense_model_name)
|
34 |
+
self.cross_encoder = CrossEncoder(cross_encoder_model)
|
35 |
+
|
36 |
+
|
37 |
+
def bm25_retrieve(self, query, top_k=70):
|
38 |
+
"""
|
39 |
+
Retrieve top K documents using BM25.
|
40 |
+
|
41 |
+
Args:
|
42 |
+
query (str): Query text.
|
43 |
+
top_k (int): Number of top BM25 documents to retrieve.
|
44 |
+
|
45 |
+
Returns:
|
46 |
+
list of dict: Top K BM25 results.
|
47 |
+
"""
|
48 |
+
cleaned_query = clean_text(query)
|
49 |
+
query_tokens = cleaned_query.split()
|
50 |
+
bm25_scores = self.bm25.get_scores(query_tokens)
|
51 |
+
top_k_indices = np.argsort(bm25_scores)[::-1][:top_k]
|
52 |
+
return self.dataset.iloc[top_k_indices].to_dict(orient='records')
|
53 |
+
|
54 |
+
|
55 |
+
def dense_retrieve(self, query, candidates=None, top_n=35):
|
56 |
+
"""
|
57 |
+
Retrieve top N documents using dense retrieval with LaBSE.
|
58 |
+
|
59 |
+
Args:
|
60 |
+
query (str): Query text.
|
61 |
+
candidates (list of dict): Candidate documents from BM25.
|
62 |
+
top_n (int): Number of top dense results to retrieve.
|
63 |
+
|
64 |
+
Returns:
|
65 |
+
list of dict: Top N dense results.
|
66 |
+
"""
|
67 |
+
if candidates is None:
|
68 |
+
candidates = self.dataset.to_dict(orient='records')
|
69 |
+
query_embedding = self.dense_model.encode(query, convert_to_tensor=True)
|
70 |
+
|
71 |
+
candidate_embeddings = torch.stack([
|
72 |
+
eval(doc['chunk_embedding'].replace('tensor', 'torch.tensor')).clone().detach()
|
73 |
+
for doc in candidates
|
74 |
+
])
|
75 |
+
|
76 |
+
similarities = util.pytorch_cos_sim(query_embedding, candidate_embeddings).squeeze(0)
|
77 |
+
top_n_indices = torch.topk(similarities, top_n).indices
|
78 |
+
return [candidates[idx] for idx in top_n_indices]
|
79 |
+
|
80 |
+
|
81 |
+
def rerank(self, query, candidates=None, top_n=3):
|
82 |
+
"""
|
83 |
+
Rerank top documents using a CrossEncoder.
|
84 |
+
|
85 |
+
Args:
|
86 |
+
query (str): Query text.
|
87 |
+
candidates (list of dict): Candidate documents from dense retriever.
|
88 |
+
top_n (int): Number of top reranked results to return.
|
89 |
+
|
90 |
+
Returns:
|
91 |
+
list of dict: Top N reranked documents.
|
92 |
+
"""
|
93 |
+
if candidates is None:
|
94 |
+
candidates = self.dataset.to_dict(orient='records')
|
95 |
+
query_document_pairs = [(query, doc['raw_text']) for doc in candidates]
|
96 |
+
scores = self.cross_encoder.predict(query_document_pairs)
|
97 |
+
top_n_indices = np.argsort(scores)[::-1][:top_n]
|
98 |
+
return [candidates[idx] for idx in top_n_indices]
|
99 |
+
|
100 |
+
|
101 |
+
|
102 |
+
def hybrid_retrieve(self, query, enable_bm25=True, enable_dense=True, enable_rerank=True, top_k_bm25=60, top_n_dense=30, top_n_rerank=2):
|
103 |
+
"""
|
104 |
+
Perform hybrid retrieval: BM25 followed by dense retrieval and optional reranking.
|
105 |
+
|
106 |
+
Args:
|
107 |
+
query (str): Query text.
|
108 |
+
top_k_bm25 (int): Number of top BM25 documents to retrieve.
|
109 |
+
top_n_dense (int): Number of top dense results to retrieve.
|
110 |
+
enable_dense (bool): Whether dense retrieval should be enabled.
|
111 |
+
enable_rerank (bool): Whether reranking should be enabled.
|
112 |
+
top_n_rerank (int): Number of top reranked documents to return.
|
113 |
+
|
114 |
+
Returns:
|
115 |
+
list of dict: Final top results after hybrid retrieval and reranking.
|
116 |
+
"""
|
117 |
+
if enable_bm25:
|
118 |
+
bm25_results = self.bm25_retrieve(query, top_k=top_k_bm25)
|
119 |
+
else:
|
120 |
+
bm25_results = None
|
121 |
+
|
122 |
+
if enable_dense:
|
123 |
+
dense_results = self.dense_retrieve(query, bm25_results, top_n=top_n_dense)
|
124 |
+
else:
|
125 |
+
dense_results = bm25_results
|
126 |
+
|
127 |
+
if enable_rerank:
|
128 |
+
final_results = self.rerank(query, dense_results, top_n=top_n_rerank)
|
129 |
+
else:
|
130 |
+
final_results = dense_results
|
131 |
+
|
132 |
+
return final_results
|
data/CountMonteCristoFull.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
data/chunked_data_corpus.csv
ADDED
The diff for this file is too large to render.
See raw diff
|
|
data/prepare_data.py
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import re
|
3 |
+
import string
|
4 |
+
from sentence_transformers import SentenceTransformer
|
5 |
+
from langchain_text_splitters import CharacterTextSplitter
|
6 |
+
import pandas as pd
|
7 |
+
|
8 |
+
DATA_FILE_PATH = os.path.join(os.path.dirname(os.path.realpath(__file__)), "CountMonteCristoFull.txt")
|
9 |
+
DENSE_RETRIEVER_MODEL_NAME = "all-MiniLM-L6-v2"
|
10 |
+
CROSS_ENCODER_MODEL_NAME = 'cross-encoder/ms-marco-MiniLM-L-12-v2'
|
11 |
+
LLM_CORE_MODEL_NAME = "groq/llama3-8b-8192"
|
12 |
+
|
13 |
+
with open(DATA_FILE_PATH, "r", encoding="utf-8") as f:
|
14 |
+
data_corpus = f.read()
|
15 |
+
|
16 |
+
splitter = CharacterTextSplitter(separator="\n\n", chunk_size=10_000, chunk_overlap=1_000)
|
17 |
+
text_chunks = splitter.create_documents([data_corpus])
|
18 |
+
|
19 |
+
prev_chapter_name = ''
|
20 |
+
for chunk in text_chunks:
|
21 |
+
chunk.metadata['belongs_to'] = set()
|
22 |
+
curr_chapter_name = ''
|
23 |
+
index_start_chapter_name = chunk.page_content.find('Chapter')
|
24 |
+
|
25 |
+
if index_start_chapter_name == -1:
|
26 |
+
curr_chapter_name = prev_chapter_name
|
27 |
+
else:
|
28 |
+
# if prev_chapter_name is not empty and next chapter start further than first 40% of the chunk.
|
29 |
+
# This means that the name of the prev chapter isn't in this chunk, but relevant info can be found.
|
30 |
+
if prev_chapter_name != '' and index_start_chapter_name > int(len(chunk.page_content) * 0.4):
|
31 |
+
chunk.metadata['belongs_to'].add(prev_chapter_name)
|
32 |
+
|
33 |
+
index_end_chapter_name = chunk.page_content.find('\n\n', index_start_chapter_name)
|
34 |
+
curr_chapter_name = chunk.page_content[index_start_chapter_name:index_end_chapter_name]
|
35 |
+
prev_chapter_name = curr_chapter_name
|
36 |
+
chunk.metadata['belongs_to'].add(curr_chapter_name)
|
37 |
+
|
38 |
+
chunk.metadata['belongs_to'] = list(chunk.metadata['belongs_to'])
|
39 |
+
|
40 |
+
|
41 |
+
def clean_text(text):
|
42 |
+
text = text.translate(str.maketrans('', '', string.punctuation))
|
43 |
+
text = text.lower()
|
44 |
+
text = re.sub(r'[^a-zA-Z0-9\s]', '', text)
|
45 |
+
text = re.sub(r'\s+', ' ', text)
|
46 |
+
|
47 |
+
return text.strip()
|
48 |
+
|
49 |
+
dense_model = SentenceTransformer(DENSE_RETRIEVER_MODEL_NAME)
|
50 |
+
|
51 |
+
def calculate_embeddings(text):
|
52 |
+
return dense_model.encode(text, convert_to_tensor=True)
|
53 |
+
|
54 |
+
chunked_data_corpus = []
|
55 |
+
|
56 |
+
for index, chunk in enumerate(text_chunks):
|
57 |
+
chunked_data_corpus.append({
|
58 |
+
'raw_text': chunk.page_content,
|
59 |
+
'cleaned_text': clean_text(chunk.page_content),
|
60 |
+
'chunk_embedding': calculate_embeddings(chunk.page_content),
|
61 |
+
'chapter_name': chunk.metadata['belongs_to']
|
62 |
+
})
|
63 |
+
|
64 |
+
chunked_data_corpus_df = pd.DataFrame(chunked_data_corpus)
|
65 |
+
|
66 |
+
chunked_data_corpus_df.to_csv('chunked_data_corpus.csv', index=False)
|
main.py
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import pandas as pd
|
3 |
+
from chatbot.bot import QuestionAnsweringBot
|
4 |
+
import os
|
5 |
+
|
6 |
+
chunked_data_corpus_df = pd.read_csv(os.path.join(os.path.dirname(os.path.realpath(__file__)), "data\\chunked_data_corpus.csv"))
|
7 |
+
|
8 |
+
bot = QuestionAnsweringBot(chunked_data_corpus_df)
|
9 |
+
|
10 |
+
def message_respond(message, history):
|
11 |
+
answer = bot.form_response(message)
|
12 |
+
return answer
|
13 |
+
|
14 |
+
gr.ChatInterface(
|
15 |
+
fn=message_respond,
|
16 |
+
type="messages",
|
17 |
+
title="RAG System for 'The Count of Monte Cristo' book",
|
18 |
+
description="Here you can ask any questions in the context of the book 'The Count of Monte Cristo'. API key is already provided.",
|
19 |
+
theme=gr.themes.Monochrome(font='Lora', text_size='lg', radius_size='sm'),
|
20 |
+
examples=["Who is Monte Cristo?",
|
21 |
+
"What is the title of Chapter 93",
|
22 |
+
"Why Edmond Dantes was in prison?",
|
23 |
+
"How many years does Edmon Dantes spent in prison?",
|
24 |
+
"Who said this sentence to whom 'Wait and hope_ (Fac et spera)'?",
|
25 |
+
"What is the title of Chapter 64?",
|
26 |
+
"Who is the president of the USA?",
|
27 |
+
"Who is the author of the book The Count of Monte Cristo?",
|
28 |
+
"Tell me about all the main identites in Monte Cristo?"
|
29 |
+
],
|
30 |
+
cache_examples=False,
|
31 |
+
).launch()
|
requirements.txt
ADDED
Binary file (4.63 kB). View file
|
|