Commit
·
7635174
0
Parent(s):
add basic UI and simple bot response
Browse files- .gitignore +13 -0
- .python-version +1 -0
- README.md +3 -0
- data/sample.pdf +0 -0
- data/sample.txt +1 -0
- pyproject.toml +34 -0
- requirements-dev.lock +278 -0
- requirements.lock +243 -0
- src/pdfchat/app.py +114 -0
.gitignore
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# python generated files
|
| 2 |
+
__pycache__/
|
| 3 |
+
*.py[oc]
|
| 4 |
+
build/
|
| 5 |
+
dist/
|
| 6 |
+
wheels/
|
| 7 |
+
*.egg-info
|
| 8 |
+
|
| 9 |
+
# venv
|
| 10 |
+
.venv
|
| 11 |
+
|
| 12 |
+
.DS_Store
|
| 13 |
+
gradio_cached_examples
|
.python-version
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
3.12.1
|
README.md
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# pdfchat
|
| 2 |
+
|
| 3 |
+
Describe your project here.
|
data/sample.pdf
ADDED
|
Binary file (204 kB). View file
|
|
|
data/sample.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
hello
|
pyproject.toml
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[project]
|
| 2 |
+
name = "pdfchat"
|
| 3 |
+
version = "0.1.0"
|
| 4 |
+
description = "Add your description here"
|
| 5 |
+
authors = [
|
| 6 |
+
{ name = "Peinan Zhang", email = "[email protected]" }
|
| 7 |
+
]
|
| 8 |
+
dependencies = [
|
| 9 |
+
"gradio>=4.19.2",
|
| 10 |
+
"langchain>=0.1.9",
|
| 11 |
+
"gradio-pdf>=0.0.5",
|
| 12 |
+
]
|
| 13 |
+
readme = "README.md"
|
| 14 |
+
requires-python = ">= 3.8"
|
| 15 |
+
|
| 16 |
+
[build-system]
|
| 17 |
+
requires = ["hatchling"]
|
| 18 |
+
build-backend = "hatchling.build"
|
| 19 |
+
|
| 20 |
+
[tool.rye]
|
| 21 |
+
managed = true
|
| 22 |
+
dev-dependencies = [
|
| 23 |
+
"icecream>=2.1.3",
|
| 24 |
+
"ipython>=8.22.1",
|
| 25 |
+
]
|
| 26 |
+
|
| 27 |
+
[tool.rye.scripts]
|
| 28 |
+
server = "python src/pdfchat/app.py"
|
| 29 |
+
|
| 30 |
+
[tool.hatch.metadata]
|
| 31 |
+
allow-direct-references = true
|
| 32 |
+
|
| 33 |
+
[tool.hatch.build.targets.wheel]
|
| 34 |
+
packages = ["src/pdfchat"]
|
requirements-dev.lock
ADDED
|
@@ -0,0 +1,278 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# generated by rye
|
| 2 |
+
# use `rye lock` or `rye sync` to update this lockfile
|
| 3 |
+
#
|
| 4 |
+
# last locked with the following flags:
|
| 5 |
+
# pre: false
|
| 6 |
+
# features: []
|
| 7 |
+
# all-features: false
|
| 8 |
+
# with-sources: false
|
| 9 |
+
|
| 10 |
+
-e file:.
|
| 11 |
+
aiofiles==23.2.1
|
| 12 |
+
# via gradio
|
| 13 |
+
aiohttp==3.9.3
|
| 14 |
+
# via langchain
|
| 15 |
+
# via langchain-community
|
| 16 |
+
aiosignal==1.3.1
|
| 17 |
+
# via aiohttp
|
| 18 |
+
altair==5.2.0
|
| 19 |
+
# via gradio
|
| 20 |
+
annotated-types==0.6.0
|
| 21 |
+
# via pydantic
|
| 22 |
+
anyio==4.3.0
|
| 23 |
+
# via httpx
|
| 24 |
+
# via langchain-core
|
| 25 |
+
# via starlette
|
| 26 |
+
asttokens==2.4.1
|
| 27 |
+
# via icecream
|
| 28 |
+
# via stack-data
|
| 29 |
+
attrs==23.2.0
|
| 30 |
+
# via aiohttp
|
| 31 |
+
# via jsonschema
|
| 32 |
+
# via referencing
|
| 33 |
+
certifi==2024.2.2
|
| 34 |
+
# via httpcore
|
| 35 |
+
# via httpx
|
| 36 |
+
# via requests
|
| 37 |
+
charset-normalizer==3.3.2
|
| 38 |
+
# via requests
|
| 39 |
+
click==8.1.7
|
| 40 |
+
# via typer
|
| 41 |
+
# via uvicorn
|
| 42 |
+
colorama==0.4.6
|
| 43 |
+
# via icecream
|
| 44 |
+
# via typer
|
| 45 |
+
contourpy==1.2.0
|
| 46 |
+
# via matplotlib
|
| 47 |
+
cycler==0.12.1
|
| 48 |
+
# via matplotlib
|
| 49 |
+
dataclasses-json==0.6.4
|
| 50 |
+
# via langchain
|
| 51 |
+
# via langchain-community
|
| 52 |
+
decorator==5.1.1
|
| 53 |
+
# via ipython
|
| 54 |
+
executing==2.0.1
|
| 55 |
+
# via icecream
|
| 56 |
+
# via stack-data
|
| 57 |
+
fastapi==0.110.0
|
| 58 |
+
# via gradio
|
| 59 |
+
ffmpy==0.3.2
|
| 60 |
+
# via gradio
|
| 61 |
+
filelock==3.13.1
|
| 62 |
+
# via huggingface-hub
|
| 63 |
+
fonttools==4.49.0
|
| 64 |
+
# via matplotlib
|
| 65 |
+
frozenlist==1.4.1
|
| 66 |
+
# via aiohttp
|
| 67 |
+
# via aiosignal
|
| 68 |
+
fsspec==2024.2.0
|
| 69 |
+
# via gradio-client
|
| 70 |
+
# via huggingface-hub
|
| 71 |
+
gradio==4.19.2
|
| 72 |
+
# via gradio-pdf
|
| 73 |
+
# via pdfchat
|
| 74 |
+
gradio-client==0.10.1
|
| 75 |
+
# via gradio
|
| 76 |
+
gradio-pdf==0.0.5
|
| 77 |
+
# via pdfchat
|
| 78 |
+
h11==0.14.0
|
| 79 |
+
# via httpcore
|
| 80 |
+
# via uvicorn
|
| 81 |
+
httpcore==1.0.4
|
| 82 |
+
# via httpx
|
| 83 |
+
httpx==0.27.0
|
| 84 |
+
# via gradio
|
| 85 |
+
# via gradio-client
|
| 86 |
+
huggingface-hub==0.20.3
|
| 87 |
+
# via gradio
|
| 88 |
+
# via gradio-client
|
| 89 |
+
icecream==2.1.3
|
| 90 |
+
idna==3.6
|
| 91 |
+
# via anyio
|
| 92 |
+
# via httpx
|
| 93 |
+
# via requests
|
| 94 |
+
# via yarl
|
| 95 |
+
importlib-resources==6.1.1
|
| 96 |
+
# via gradio
|
| 97 |
+
ipython==8.22.1
|
| 98 |
+
jedi==0.19.1
|
| 99 |
+
# via ipython
|
| 100 |
+
jinja2==3.1.3
|
| 101 |
+
# via altair
|
| 102 |
+
# via gradio
|
| 103 |
+
jsonpatch==1.33
|
| 104 |
+
# via langchain
|
| 105 |
+
# via langchain-core
|
| 106 |
+
jsonpointer==2.4
|
| 107 |
+
# via jsonpatch
|
| 108 |
+
jsonschema==4.21.1
|
| 109 |
+
# via altair
|
| 110 |
+
jsonschema-specifications==2023.12.1
|
| 111 |
+
# via jsonschema
|
| 112 |
+
kiwisolver==1.4.5
|
| 113 |
+
# via matplotlib
|
| 114 |
+
langchain==0.1.9
|
| 115 |
+
# via pdfchat
|
| 116 |
+
langchain-community==0.0.24
|
| 117 |
+
# via langchain
|
| 118 |
+
langchain-core==0.1.26
|
| 119 |
+
# via langchain
|
| 120 |
+
# via langchain-community
|
| 121 |
+
langsmith==0.1.8
|
| 122 |
+
# via langchain
|
| 123 |
+
# via langchain-community
|
| 124 |
+
# via langchain-core
|
| 125 |
+
markdown-it-py==3.0.0
|
| 126 |
+
# via rich
|
| 127 |
+
markupsafe==2.1.5
|
| 128 |
+
# via gradio
|
| 129 |
+
# via jinja2
|
| 130 |
+
marshmallow==3.20.2
|
| 131 |
+
# via dataclasses-json
|
| 132 |
+
matplotlib==3.8.3
|
| 133 |
+
# via gradio
|
| 134 |
+
matplotlib-inline==0.1.6
|
| 135 |
+
# via ipython
|
| 136 |
+
mdurl==0.1.2
|
| 137 |
+
# via markdown-it-py
|
| 138 |
+
multidict==6.0.5
|
| 139 |
+
# via aiohttp
|
| 140 |
+
# via yarl
|
| 141 |
+
mypy-extensions==1.0.0
|
| 142 |
+
# via typing-inspect
|
| 143 |
+
numpy==1.26.4
|
| 144 |
+
# via altair
|
| 145 |
+
# via contourpy
|
| 146 |
+
# via gradio
|
| 147 |
+
# via langchain
|
| 148 |
+
# via langchain-community
|
| 149 |
+
# via matplotlib
|
| 150 |
+
# via pandas
|
| 151 |
+
orjson==3.9.15
|
| 152 |
+
# via gradio
|
| 153 |
+
# via langsmith
|
| 154 |
+
packaging==23.2
|
| 155 |
+
# via altair
|
| 156 |
+
# via gradio
|
| 157 |
+
# via gradio-client
|
| 158 |
+
# via huggingface-hub
|
| 159 |
+
# via langchain-core
|
| 160 |
+
# via marshmallow
|
| 161 |
+
# via matplotlib
|
| 162 |
+
pandas==2.2.1
|
| 163 |
+
# via altair
|
| 164 |
+
# via gradio
|
| 165 |
+
parso==0.8.3
|
| 166 |
+
# via jedi
|
| 167 |
+
pexpect==4.9.0
|
| 168 |
+
# via ipython
|
| 169 |
+
pillow==10.2.0
|
| 170 |
+
# via gradio
|
| 171 |
+
# via matplotlib
|
| 172 |
+
prompt-toolkit==3.0.43
|
| 173 |
+
# via ipython
|
| 174 |
+
ptyprocess==0.7.0
|
| 175 |
+
# via pexpect
|
| 176 |
+
pure-eval==0.2.2
|
| 177 |
+
# via stack-data
|
| 178 |
+
pydantic==2.6.2
|
| 179 |
+
# via fastapi
|
| 180 |
+
# via gradio
|
| 181 |
+
# via langchain
|
| 182 |
+
# via langchain-core
|
| 183 |
+
# via langsmith
|
| 184 |
+
pydantic-core==2.16.3
|
| 185 |
+
# via pydantic
|
| 186 |
+
pydub==0.25.1
|
| 187 |
+
# via gradio
|
| 188 |
+
pygments==2.17.2
|
| 189 |
+
# via icecream
|
| 190 |
+
# via ipython
|
| 191 |
+
# via rich
|
| 192 |
+
pyparsing==3.1.1
|
| 193 |
+
# via matplotlib
|
| 194 |
+
python-dateutil==2.8.2
|
| 195 |
+
# via matplotlib
|
| 196 |
+
# via pandas
|
| 197 |
+
python-multipart==0.0.9
|
| 198 |
+
# via gradio
|
| 199 |
+
pytz==2024.1
|
| 200 |
+
# via pandas
|
| 201 |
+
pyyaml==6.0.1
|
| 202 |
+
# via gradio
|
| 203 |
+
# via huggingface-hub
|
| 204 |
+
# via langchain
|
| 205 |
+
# via langchain-community
|
| 206 |
+
# via langchain-core
|
| 207 |
+
referencing==0.33.0
|
| 208 |
+
# via jsonschema
|
| 209 |
+
# via jsonschema-specifications
|
| 210 |
+
requests==2.31.0
|
| 211 |
+
# via huggingface-hub
|
| 212 |
+
# via langchain
|
| 213 |
+
# via langchain-community
|
| 214 |
+
# via langchain-core
|
| 215 |
+
# via langsmith
|
| 216 |
+
rich==13.7.0
|
| 217 |
+
# via typer
|
| 218 |
+
rpds-py==0.18.0
|
| 219 |
+
# via jsonschema
|
| 220 |
+
# via referencing
|
| 221 |
+
ruff==0.2.2
|
| 222 |
+
# via gradio
|
| 223 |
+
semantic-version==2.10.0
|
| 224 |
+
# via gradio
|
| 225 |
+
shellingham==1.5.4
|
| 226 |
+
# via typer
|
| 227 |
+
six==1.16.0
|
| 228 |
+
# via asttokens
|
| 229 |
+
# via python-dateutil
|
| 230 |
+
sniffio==1.3.0
|
| 231 |
+
# via anyio
|
| 232 |
+
# via httpx
|
| 233 |
+
sqlalchemy==2.0.27
|
| 234 |
+
# via langchain
|
| 235 |
+
# via langchain-community
|
| 236 |
+
stack-data==0.6.3
|
| 237 |
+
# via ipython
|
| 238 |
+
starlette==0.36.3
|
| 239 |
+
# via fastapi
|
| 240 |
+
tenacity==8.2.3
|
| 241 |
+
# via langchain
|
| 242 |
+
# via langchain-community
|
| 243 |
+
# via langchain-core
|
| 244 |
+
tomlkit==0.12.0
|
| 245 |
+
# via gradio
|
| 246 |
+
toolz==0.12.1
|
| 247 |
+
# via altair
|
| 248 |
+
tqdm==4.66.2
|
| 249 |
+
# via huggingface-hub
|
| 250 |
+
traitlets==5.14.1
|
| 251 |
+
# via ipython
|
| 252 |
+
# via matplotlib-inline
|
| 253 |
+
typer==0.9.0
|
| 254 |
+
# via gradio
|
| 255 |
+
typing-extensions==4.9.0
|
| 256 |
+
# via fastapi
|
| 257 |
+
# via gradio
|
| 258 |
+
# via gradio-client
|
| 259 |
+
# via huggingface-hub
|
| 260 |
+
# via pydantic
|
| 261 |
+
# via pydantic-core
|
| 262 |
+
# via sqlalchemy
|
| 263 |
+
# via typer
|
| 264 |
+
# via typing-inspect
|
| 265 |
+
typing-inspect==0.9.0
|
| 266 |
+
# via dataclasses-json
|
| 267 |
+
tzdata==2024.1
|
| 268 |
+
# via pandas
|
| 269 |
+
urllib3==2.2.1
|
| 270 |
+
# via requests
|
| 271 |
+
uvicorn==0.27.1
|
| 272 |
+
# via gradio
|
| 273 |
+
wcwidth==0.2.13
|
| 274 |
+
# via prompt-toolkit
|
| 275 |
+
websockets==11.0.3
|
| 276 |
+
# via gradio-client
|
| 277 |
+
yarl==1.9.4
|
| 278 |
+
# via aiohttp
|
requirements.lock
ADDED
|
@@ -0,0 +1,243 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# generated by rye
|
| 2 |
+
# use `rye lock` or `rye sync` to update this lockfile
|
| 3 |
+
#
|
| 4 |
+
# last locked with the following flags:
|
| 5 |
+
# pre: false
|
| 6 |
+
# features: []
|
| 7 |
+
# all-features: false
|
| 8 |
+
# with-sources: false
|
| 9 |
+
|
| 10 |
+
-e file:.
|
| 11 |
+
aiofiles==23.2.1
|
| 12 |
+
# via gradio
|
| 13 |
+
aiohttp==3.9.3
|
| 14 |
+
# via langchain
|
| 15 |
+
# via langchain-community
|
| 16 |
+
aiosignal==1.3.1
|
| 17 |
+
# via aiohttp
|
| 18 |
+
altair==5.2.0
|
| 19 |
+
# via gradio
|
| 20 |
+
annotated-types==0.6.0
|
| 21 |
+
# via pydantic
|
| 22 |
+
anyio==4.3.0
|
| 23 |
+
# via httpx
|
| 24 |
+
# via langchain-core
|
| 25 |
+
# via starlette
|
| 26 |
+
attrs==23.2.0
|
| 27 |
+
# via aiohttp
|
| 28 |
+
# via jsonschema
|
| 29 |
+
# via referencing
|
| 30 |
+
certifi==2024.2.2
|
| 31 |
+
# via httpcore
|
| 32 |
+
# via httpx
|
| 33 |
+
# via requests
|
| 34 |
+
charset-normalizer==3.3.2
|
| 35 |
+
# via requests
|
| 36 |
+
click==8.1.7
|
| 37 |
+
# via typer
|
| 38 |
+
# via uvicorn
|
| 39 |
+
colorama==0.4.6
|
| 40 |
+
# via typer
|
| 41 |
+
contourpy==1.2.0
|
| 42 |
+
# via matplotlib
|
| 43 |
+
cycler==0.12.1
|
| 44 |
+
# via matplotlib
|
| 45 |
+
dataclasses-json==0.6.4
|
| 46 |
+
# via langchain
|
| 47 |
+
# via langchain-community
|
| 48 |
+
fastapi==0.110.0
|
| 49 |
+
# via gradio
|
| 50 |
+
ffmpy==0.3.2
|
| 51 |
+
# via gradio
|
| 52 |
+
filelock==3.13.1
|
| 53 |
+
# via huggingface-hub
|
| 54 |
+
fonttools==4.49.0
|
| 55 |
+
# via matplotlib
|
| 56 |
+
frozenlist==1.4.1
|
| 57 |
+
# via aiohttp
|
| 58 |
+
# via aiosignal
|
| 59 |
+
fsspec==2024.2.0
|
| 60 |
+
# via gradio-client
|
| 61 |
+
# via huggingface-hub
|
| 62 |
+
gradio==4.19.2
|
| 63 |
+
# via gradio-pdf
|
| 64 |
+
# via pdfchat
|
| 65 |
+
gradio-client==0.10.1
|
| 66 |
+
# via gradio
|
| 67 |
+
gradio-pdf==0.0.5
|
| 68 |
+
# via pdfchat
|
| 69 |
+
h11==0.14.0
|
| 70 |
+
# via httpcore
|
| 71 |
+
# via uvicorn
|
| 72 |
+
httpcore==1.0.4
|
| 73 |
+
# via httpx
|
| 74 |
+
httpx==0.27.0
|
| 75 |
+
# via gradio
|
| 76 |
+
# via gradio-client
|
| 77 |
+
huggingface-hub==0.20.3
|
| 78 |
+
# via gradio
|
| 79 |
+
# via gradio-client
|
| 80 |
+
idna==3.6
|
| 81 |
+
# via anyio
|
| 82 |
+
# via httpx
|
| 83 |
+
# via requests
|
| 84 |
+
# via yarl
|
| 85 |
+
importlib-resources==6.1.1
|
| 86 |
+
# via gradio
|
| 87 |
+
jinja2==3.1.3
|
| 88 |
+
# via altair
|
| 89 |
+
# via gradio
|
| 90 |
+
jsonpatch==1.33
|
| 91 |
+
# via langchain
|
| 92 |
+
# via langchain-core
|
| 93 |
+
jsonpointer==2.4
|
| 94 |
+
# via jsonpatch
|
| 95 |
+
jsonschema==4.21.1
|
| 96 |
+
# via altair
|
| 97 |
+
jsonschema-specifications==2023.12.1
|
| 98 |
+
# via jsonschema
|
| 99 |
+
kiwisolver==1.4.5
|
| 100 |
+
# via matplotlib
|
| 101 |
+
langchain==0.1.9
|
| 102 |
+
# via pdfchat
|
| 103 |
+
langchain-community==0.0.24
|
| 104 |
+
# via langchain
|
| 105 |
+
langchain-core==0.1.26
|
| 106 |
+
# via langchain
|
| 107 |
+
# via langchain-community
|
| 108 |
+
langsmith==0.1.8
|
| 109 |
+
# via langchain
|
| 110 |
+
# via langchain-community
|
| 111 |
+
# via langchain-core
|
| 112 |
+
markdown-it-py==3.0.0
|
| 113 |
+
# via rich
|
| 114 |
+
markupsafe==2.1.5
|
| 115 |
+
# via gradio
|
| 116 |
+
# via jinja2
|
| 117 |
+
marshmallow==3.20.2
|
| 118 |
+
# via dataclasses-json
|
| 119 |
+
matplotlib==3.8.3
|
| 120 |
+
# via gradio
|
| 121 |
+
mdurl==0.1.2
|
| 122 |
+
# via markdown-it-py
|
| 123 |
+
multidict==6.0.5
|
| 124 |
+
# via aiohttp
|
| 125 |
+
# via yarl
|
| 126 |
+
mypy-extensions==1.0.0
|
| 127 |
+
# via typing-inspect
|
| 128 |
+
numpy==1.26.4
|
| 129 |
+
# via altair
|
| 130 |
+
# via contourpy
|
| 131 |
+
# via gradio
|
| 132 |
+
# via langchain
|
| 133 |
+
# via langchain-community
|
| 134 |
+
# via matplotlib
|
| 135 |
+
# via pandas
|
| 136 |
+
orjson==3.9.15
|
| 137 |
+
# via gradio
|
| 138 |
+
# via langsmith
|
| 139 |
+
packaging==23.2
|
| 140 |
+
# via altair
|
| 141 |
+
# via gradio
|
| 142 |
+
# via gradio-client
|
| 143 |
+
# via huggingface-hub
|
| 144 |
+
# via langchain-core
|
| 145 |
+
# via marshmallow
|
| 146 |
+
# via matplotlib
|
| 147 |
+
pandas==2.2.1
|
| 148 |
+
# via altair
|
| 149 |
+
# via gradio
|
| 150 |
+
pillow==10.2.0
|
| 151 |
+
# via gradio
|
| 152 |
+
# via matplotlib
|
| 153 |
+
pydantic==2.6.2
|
| 154 |
+
# via fastapi
|
| 155 |
+
# via gradio
|
| 156 |
+
# via langchain
|
| 157 |
+
# via langchain-core
|
| 158 |
+
# via langsmith
|
| 159 |
+
pydantic-core==2.16.3
|
| 160 |
+
# via pydantic
|
| 161 |
+
pydub==0.25.1
|
| 162 |
+
# via gradio
|
| 163 |
+
pygments==2.17.2
|
| 164 |
+
# via rich
|
| 165 |
+
pyparsing==3.1.1
|
| 166 |
+
# via matplotlib
|
| 167 |
+
python-dateutil==2.8.2
|
| 168 |
+
# via matplotlib
|
| 169 |
+
# via pandas
|
| 170 |
+
python-multipart==0.0.9
|
| 171 |
+
# via gradio
|
| 172 |
+
pytz==2024.1
|
| 173 |
+
# via pandas
|
| 174 |
+
pyyaml==6.0.1
|
| 175 |
+
# via gradio
|
| 176 |
+
# via huggingface-hub
|
| 177 |
+
# via langchain
|
| 178 |
+
# via langchain-community
|
| 179 |
+
# via langchain-core
|
| 180 |
+
referencing==0.33.0
|
| 181 |
+
# via jsonschema
|
| 182 |
+
# via jsonschema-specifications
|
| 183 |
+
requests==2.31.0
|
| 184 |
+
# via huggingface-hub
|
| 185 |
+
# via langchain
|
| 186 |
+
# via langchain-community
|
| 187 |
+
# via langchain-core
|
| 188 |
+
# via langsmith
|
| 189 |
+
rich==13.7.0
|
| 190 |
+
# via typer
|
| 191 |
+
rpds-py==0.18.0
|
| 192 |
+
# via jsonschema
|
| 193 |
+
# via referencing
|
| 194 |
+
ruff==0.2.2
|
| 195 |
+
# via gradio
|
| 196 |
+
semantic-version==2.10.0
|
| 197 |
+
# via gradio
|
| 198 |
+
shellingham==1.5.4
|
| 199 |
+
# via typer
|
| 200 |
+
six==1.16.0
|
| 201 |
+
# via python-dateutil
|
| 202 |
+
sniffio==1.3.0
|
| 203 |
+
# via anyio
|
| 204 |
+
# via httpx
|
| 205 |
+
sqlalchemy==2.0.27
|
| 206 |
+
# via langchain
|
| 207 |
+
# via langchain-community
|
| 208 |
+
starlette==0.36.3
|
| 209 |
+
# via fastapi
|
| 210 |
+
tenacity==8.2.3
|
| 211 |
+
# via langchain
|
| 212 |
+
# via langchain-community
|
| 213 |
+
# via langchain-core
|
| 214 |
+
tomlkit==0.12.0
|
| 215 |
+
# via gradio
|
| 216 |
+
toolz==0.12.1
|
| 217 |
+
# via altair
|
| 218 |
+
tqdm==4.66.2
|
| 219 |
+
# via huggingface-hub
|
| 220 |
+
typer==0.9.0
|
| 221 |
+
# via gradio
|
| 222 |
+
typing-extensions==4.9.0
|
| 223 |
+
# via fastapi
|
| 224 |
+
# via gradio
|
| 225 |
+
# via gradio-client
|
| 226 |
+
# via huggingface-hub
|
| 227 |
+
# via pydantic
|
| 228 |
+
# via pydantic-core
|
| 229 |
+
# via sqlalchemy
|
| 230 |
+
# via typer
|
| 231 |
+
# via typing-inspect
|
| 232 |
+
typing-inspect==0.9.0
|
| 233 |
+
# via dataclasses-json
|
| 234 |
+
tzdata==2024.1
|
| 235 |
+
# via pandas
|
| 236 |
+
urllib3==2.2.1
|
| 237 |
+
# via requests
|
| 238 |
+
uvicorn==0.27.1
|
| 239 |
+
# via gradio
|
| 240 |
+
websockets==11.0.3
|
| 241 |
+
# via gradio-client
|
| 242 |
+
yarl==1.9.4
|
| 243 |
+
# via aiohttp
|
src/pdfchat/app.py
ADDED
|
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import time
|
| 2 |
+
from dataclasses import dataclass
|
| 3 |
+
from pathlib import Path
|
| 4 |
+
|
| 5 |
+
import gradio as gr
|
| 6 |
+
from icecream import ic
|
| 7 |
+
|
| 8 |
+
MODEL_CALM2 = "cyberagent/calm2"
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
@dataclass
|
| 12 |
+
class Chat:
|
| 13 |
+
query: str
|
| 14 |
+
response: str | None
|
| 15 |
+
|
| 16 |
+
def to_list(self) -> list[str, str]:
|
| 17 |
+
return [self.query, self.response]
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
@dataclass
|
| 21 |
+
class ChatHistory:
|
| 22 |
+
history: list[Chat]
|
| 23 |
+
|
| 24 |
+
def __init__(self, history: list[tuple[str, str] | list[str, str]] | None = None):
|
| 25 |
+
if history is None:
|
| 26 |
+
self.history = []
|
| 27 |
+
else:
|
| 28 |
+
self.history = [Chat(*chat) for chat in history]
|
| 29 |
+
|
| 30 |
+
def __iter__(self):
|
| 31 |
+
return iter([chat.to_list() for chat in self.history])
|
| 32 |
+
|
| 33 |
+
def __getitem__(self, index: int) -> Chat:
|
| 34 |
+
return self.history[index]
|
| 35 |
+
|
| 36 |
+
def add_chat(self, chat: Chat):
|
| 37 |
+
self.history.append(chat)
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
def open_file(file_path: str) -> str:
|
| 41 |
+
file_path = Path(file_path)
|
| 42 |
+
if file_path.suffix == ".txt":
|
| 43 |
+
text = file_path.read_text()
|
| 44 |
+
elif file_path.suffix == ".pdf":
|
| 45 |
+
text = "WARNING: PDF file is not supported yet."
|
| 46 |
+
else:
|
| 47 |
+
gr.exit("Unsupported file type.")
|
| 48 |
+
|
| 49 |
+
return text
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
def bot(history: ChatHistory, query: str, file_path: str) -> ChatHistory:
|
| 53 |
+
history = ChatHistory(history)
|
| 54 |
+
if not file_path:
|
| 55 |
+
history.add_chat(Chat(query=query, response=None))
|
| 56 |
+
return history
|
| 57 |
+
document = open_file(file_path)
|
| 58 |
+
history.add_chat(Chat(query=query, response=document))
|
| 59 |
+
ic(history)
|
| 60 |
+
|
| 61 |
+
# TODO: use streaming inference
|
| 62 |
+
return history
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
with gr.Blocks() as app:
|
| 66 |
+
with gr.Row():
|
| 67 |
+
with gr.Column(scale=0.4):
|
| 68 |
+
model_name = gr.Dropdown(
|
| 69 |
+
choices=[MODEL_CALM2],
|
| 70 |
+
value=MODEL_CALM2,
|
| 71 |
+
label="Model",
|
| 72 |
+
)
|
| 73 |
+
file_box = gr.File(
|
| 74 |
+
label="Document",
|
| 75 |
+
file_types=[".pdf", ".txt"],
|
| 76 |
+
file_count="single",
|
| 77 |
+
container=False,
|
| 78 |
+
)
|
| 79 |
+
gr.Examples(
|
| 80 |
+
examples=[["data/sample.txt"], ["data/sample.pdf"]],
|
| 81 |
+
inputs=[file_box],
|
| 82 |
+
outputs=[],
|
| 83 |
+
fn=lambda model_name, document: None,
|
| 84 |
+
)
|
| 85 |
+
with gr.Accordion("Parameters", open=False):
|
| 86 |
+
temperature_slider = gr.Slider(
|
| 87 |
+
minimum=0.1, maximum=1.0, value=0.5, label="Temperature"
|
| 88 |
+
)
|
| 89 |
+
temperature_slider.change(lambda x: x, [temperature_slider])
|
| 90 |
+
top_p_slider = gr.Slider(
|
| 91 |
+
minimum=0.1, maximum=1.0, value=0.5, label="Top P"
|
| 92 |
+
)
|
| 93 |
+
top_p_slider.change(lambda x: x, [top_p_slider])
|
| 94 |
+
with gr.Column(scale=0.6):
|
| 95 |
+
chatbot = gr.Chatbot(
|
| 96 |
+
bubble_full_width=False,
|
| 97 |
+
height=650,
|
| 98 |
+
)
|
| 99 |
+
ic(chatbot)
|
| 100 |
+
with gr.Row():
|
| 101 |
+
text_box = gr.Textbox(
|
| 102 |
+
scale=0.9,
|
| 103 |
+
show_label=False,
|
| 104 |
+
placeholder="Type your message here",
|
| 105 |
+
container=False,
|
| 106 |
+
)
|
| 107 |
+
submit_button = gr.Button("Submit", scale=0.1, variant="primary")
|
| 108 |
+
submit = submit_button.click(
|
| 109 |
+
fn=bot,
|
| 110 |
+
inputs=[chatbot, text_box, file_box],
|
| 111 |
+
outputs=chatbot,
|
| 112 |
+
)
|
| 113 |
+
|
| 114 |
+
app.queue().launch(debug=True)
|