Spaces:
Running
Running
Sophia Yang
commited on
Commit
•
97aaeb6
1
Parent(s):
e5c24ed
add files
Browse files- Dockerfile +28 -0
- LangChain_QA_Panel_App.ipynb +239 -0
- requirements.txt +6 -0
Dockerfile
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# FROM python:3.9
|
2 |
+
FROM nvidia/cuda:11.7.1-cudnn8-devel-ubuntu22.04
|
3 |
+
LABEL maintainer="Hugging Face"
|
4 |
+
LABEL repository="transformers"
|
5 |
+
|
6 |
+
RUN apt update && \
|
7 |
+
apt install -y bash \
|
8 |
+
build-essential \
|
9 |
+
git \
|
10 |
+
curl \
|
11 |
+
ca-certificates \
|
12 |
+
python3 \
|
13 |
+
python3-pip && \
|
14 |
+
rm -rf /var/lib/apt/lists
|
15 |
+
|
16 |
+
|
17 |
+
WORKDIR /code
|
18 |
+
|
19 |
+
COPY ./requirements.txt /code/requirements.txt
|
20 |
+
RUN python3 -m pip install --no-cache-dir --upgrade pip
|
21 |
+
RUN python3 -m pip install --no-cache-dir --upgrade -r /code/requirements.txt
|
22 |
+
|
23 |
+
COPY . .
|
24 |
+
|
25 |
+
CMD ["panel", "serve", "/code/LangChain_QA_Panel_App.ipynb", "--address", "0.0.0.0", "--port", "7860", "--allow-websocket-origin", "sophiamyang-panel-pdf-qa.hf.space", "--allow-websocket-origin", "0.0.0.0:7860"]
|
26 |
+
|
27 |
+
RUN mkdir /.cache
|
28 |
+
RUN chmod 777 /.cache
|
LangChain_QA_Panel_App.ipynb
ADDED
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"attachments": {},
|
5 |
+
"cell_type": "markdown",
|
6 |
+
"id": "04815d1b-44ee-4bd3-878e-fa0c3bf9fa7f",
|
7 |
+
"metadata": {
|
8 |
+
"tags": []
|
9 |
+
},
|
10 |
+
"source": [
|
11 |
+
"# LangChain QA Panel App\n",
|
12 |
+
"\n",
|
13 |
+
"This notebook shows how to make this app:"
|
14 |
+
]
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"cell_type": "code",
|
18 |
+
"execution_count": null,
|
19 |
+
"id": "a181568b-9cde-4a55-a853-4d2a41dbfdad",
|
20 |
+
"metadata": {
|
21 |
+
"tags": []
|
22 |
+
},
|
23 |
+
"outputs": [],
|
24 |
+
"source": [
|
25 |
+
"#!pip install langchain openai chromadb tiktoken pypdf panel\n"
|
26 |
+
]
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"cell_type": "code",
|
30 |
+
"execution_count": null,
|
31 |
+
"id": "9a464409-d064-4766-a9cb-5119f6c4b8f5",
|
32 |
+
"metadata": {
|
33 |
+
"tags": []
|
34 |
+
},
|
35 |
+
"outputs": [],
|
36 |
+
"source": [
|
37 |
+
"import os \n",
|
38 |
+
"from langchain.chains import RetrievalQA\n",
|
39 |
+
"from langchain.llms import OpenAI\n",
|
40 |
+
"from langchain.document_loaders import TextLoader\n",
|
41 |
+
"from langchain.document_loaders import PyPDFLoader\n",
|
42 |
+
"from langchain.indexes import VectorstoreIndexCreator\n",
|
43 |
+
"from langchain.text_splitter import CharacterTextSplitter\n",
|
44 |
+
"from langchain.embeddings import OpenAIEmbeddings\n",
|
45 |
+
"from langchain.vectorstores import Chroma\n",
|
46 |
+
"import panel as pn\n",
|
47 |
+
"import tempfile\n"
|
48 |
+
]
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"cell_type": "code",
|
52 |
+
"execution_count": null,
|
53 |
+
"id": "b2d07ea5-9ff2-4c96-a8dc-92895d870b73",
|
54 |
+
"metadata": {
|
55 |
+
"tags": []
|
56 |
+
},
|
57 |
+
"outputs": [],
|
58 |
+
"source": [
|
59 |
+
"pn.extension('texteditor', template=\"bootstrap\", sizing_mode='stretch_width')\n",
|
60 |
+
"pn.state.template.param.update(\n",
|
61 |
+
" main_max_width=\"690px\",\n",
|
62 |
+
" header_background=\"#F08080\",\n",
|
63 |
+
")"
|
64 |
+
]
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"cell_type": "code",
|
68 |
+
"execution_count": null,
|
69 |
+
"id": "763db4d0-3436-41d3-8b0f-e66ce16468cd",
|
70 |
+
"metadata": {
|
71 |
+
"tags": []
|
72 |
+
},
|
73 |
+
"outputs": [],
|
74 |
+
"source": [
|
75 |
+
"file_input = pn.widgets.FileInput(width=300)\n",
|
76 |
+
"\n",
|
77 |
+
"openaikey = pn.widgets.PasswordInput(\n",
|
78 |
+
" value=\"\", placeholder=\"Enter your OpenAI API Key here...\", width=300\n",
|
79 |
+
")\n",
|
80 |
+
"prompt = pn.widgets.TextEditor(\n",
|
81 |
+
" value=\"\", placeholder=\"Enter your questions here...\", height=160, toolbar=False\n",
|
82 |
+
")\n",
|
83 |
+
"run_button = pn.widgets.Button(name=\"Run!\")\n",
|
84 |
+
"\n",
|
85 |
+
"select_k = pn.widgets.IntSlider(\n",
|
86 |
+
" name=\"Number of relevant chunks\", start=1, end=5, step=1, value=2\n",
|
87 |
+
")\n",
|
88 |
+
"select_chain_type = pn.widgets.RadioButtonGroup(\n",
|
89 |
+
" name='Chain type', \n",
|
90 |
+
" options=['stuff', 'map_reduce', \"refine\", \"map_rerank\"]\n",
|
91 |
+
")\n",
|
92 |
+
"\n",
|
93 |
+
"widgets = pn.Row(\n",
|
94 |
+
" pn.Column(prompt, run_button, margin=5),\n",
|
95 |
+
" pn.Card(\n",
|
96 |
+
" \"Chain type:\",\n",
|
97 |
+
" pn.Column(select_chain_type, select_k),\n",
|
98 |
+
" title=\"Advanced settings\", margin=10\n",
|
99 |
+
" ), width=600\n",
|
100 |
+
")"
|
101 |
+
]
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"cell_type": "code",
|
105 |
+
"execution_count": null,
|
106 |
+
"id": "9b83cc06-3401-498f-8f84-8a98370f3121",
|
107 |
+
"metadata": {
|
108 |
+
"tags": []
|
109 |
+
},
|
110 |
+
"outputs": [],
|
111 |
+
"source": [
|
112 |
+
"def qa(file, query, chain_type, k):\n",
|
113 |
+
" # load document\n",
|
114 |
+
" loader = PyPDFLoader(file)\n",
|
115 |
+
" documents = loader.load()\n",
|
116 |
+
" # split the documents into chunks\n",
|
117 |
+
" text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
118 |
+
" texts = text_splitter.split_documents(documents)\n",
|
119 |
+
" # select which embeddings we want to use\n",
|
120 |
+
" embeddings = OpenAIEmbeddings()\n",
|
121 |
+
" # create the vectorestore to use as the index\n",
|
122 |
+
" db = Chroma.from_documents(texts, embeddings)\n",
|
123 |
+
" # expose this index in a retriever interface\n",
|
124 |
+
" retriever = db.as_retriever(search_type=\"similarity\", search_kwargs={\"k\": k})\n",
|
125 |
+
" # create a chain to answer questions \n",
|
126 |
+
" qa = RetrievalQA.from_chain_type(\n",
|
127 |
+
" llm=OpenAI(), chain_type=chain_type, retriever=retriever, return_source_documents=True)\n",
|
128 |
+
" result = qa({\"query\": query})\n",
|
129 |
+
" print(result['result'])\n",
|
130 |
+
" return result"
|
131 |
+
]
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"cell_type": "code",
|
135 |
+
"execution_count": null,
|
136 |
+
"id": "2722f43b-daf6-4d17-a842-41203ae9b140",
|
137 |
+
"metadata": {
|
138 |
+
"tags": []
|
139 |
+
},
|
140 |
+
"outputs": [],
|
141 |
+
"source": [
|
142 |
+
"# result = qa(\"example.pdf\", \"what is the total number of AI publications?\")"
|
143 |
+
]
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"cell_type": "code",
|
147 |
+
"execution_count": null,
|
148 |
+
"id": "60e1b3d3-c0d2-4260-ae0c-26b03f1b8824",
|
149 |
+
"metadata": {},
|
150 |
+
"outputs": [],
|
151 |
+
"source": [
|
152 |
+
"convos = [] # store all panel objects in a list\n",
|
153 |
+
"\n",
|
154 |
+
"def qa_result(_):\n",
|
155 |
+
" os.environ[\"OPENAI_API_KEY\"] = openaikey.value\n",
|
156 |
+
" \n",
|
157 |
+
" # save pdf file to a temp file \n",
|
158 |
+
" if file_input.value is not None:\n",
|
159 |
+
" file_input.save(\"temp.pdf\")\n",
|
160 |
+
" \n",
|
161 |
+
" prompt_text = prompt.value\n",
|
162 |
+
" if prompt_text:\n",
|
163 |
+
" result = qa(file=\"temp.pdf\", query=prompt_text, chain_type=select_chain_type.value, k=select_k.value)\n",
|
164 |
+
" convos.extend([\n",
|
165 |
+
" pn.Row(\n",
|
166 |
+
" pn.panel(\"\\U0001F60A\", width=10),\n",
|
167 |
+
" prompt_text,\n",
|
168 |
+
" width=600\n",
|
169 |
+
" ),\n",
|
170 |
+
" pn.Row(\n",
|
171 |
+
" pn.panel(\"\\U0001F916\", width=10),\n",
|
172 |
+
" pn.Column(\n",
|
173 |
+
" result[\"result\"],\n",
|
174 |
+
" \"Relevant source text:\",\n",
|
175 |
+
" pn.pane.Markdown('\\n--------------------------------------------------------------------\\n'.join(doc.page_content for doc in result[\"source_documents\"]))\n",
|
176 |
+
" )\n",
|
177 |
+
" )\n",
|
178 |
+
" ])\n",
|
179 |
+
" #return convos\n",
|
180 |
+
" return pn.Column(*convos, margin=15, width=575, min_height=400)\n"
|
181 |
+
]
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"cell_type": "code",
|
185 |
+
"execution_count": null,
|
186 |
+
"id": "c3a70857-0b98-4f62-a9c0-b62ca42b474c",
|
187 |
+
"metadata": {
|
188 |
+
"tags": []
|
189 |
+
},
|
190 |
+
"outputs": [],
|
191 |
+
"source": [
|
192 |
+
"qa_interactive = pn.panel(\n",
|
193 |
+
" pn.bind(qa_result, run_button),\n",
|
194 |
+
" loading_indicator=True\n",
|
195 |
+
")"
|
196 |
+
]
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"cell_type": "code",
|
200 |
+
"execution_count": null,
|
201 |
+
"id": "1b0ec253-2bcd-4f91-96d8-d8456e900a58",
|
202 |
+
"metadata": {
|
203 |
+
"tags": []
|
204 |
+
},
|
205 |
+
"outputs": [],
|
206 |
+
"source": [
|
207 |
+
"# layout\n",
|
208 |
+
"pn.Column(\n",
|
209 |
+
" \"## \\U0001F60A! Question Answering with your PDF file\",\n",
|
210 |
+
" pn.Row(file_input,openaikey),\n",
|
211 |
+
" qa_interactive,\n",
|
212 |
+
" widgets\n",
|
213 |
+
"\n",
|
214 |
+
").servable()"
|
215 |
+
]
|
216 |
+
}
|
217 |
+
],
|
218 |
+
"metadata": {
|
219 |
+
"kernelspec": {
|
220 |
+
"display_name": "Python 3 (ipykernel)",
|
221 |
+
"language": "python",
|
222 |
+
"name": "python3"
|
223 |
+
},
|
224 |
+
"language_info": {
|
225 |
+
"codemirror_mode": {
|
226 |
+
"name": "ipython",
|
227 |
+
"version": 3
|
228 |
+
},
|
229 |
+
"file_extension": ".py",
|
230 |
+
"mimetype": "text/x-python",
|
231 |
+
"name": "python",
|
232 |
+
"nbconvert_exporter": "python",
|
233 |
+
"pygments_lexer": "ipython3",
|
234 |
+
"version": "3.10.10"
|
235 |
+
}
|
236 |
+
},
|
237 |
+
"nbformat": 4,
|
238 |
+
"nbformat_minor": 5
|
239 |
+
}
|
requirements.txt
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
langchain
|
2 |
+
openai
|
3 |
+
chromadb
|
4 |
+
pypdf
|
5 |
+
panel
|
6 |
+
notebook
|