Spaces:
Sleeping
Sleeping
updated UI
Browse files- .gitignore +165 -0
- app.py +24 -24
- tmp_docs/empty.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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/#use-with-ide
|
110 |
+
.pdm.toml
|
111 |
+
|
112 |
+
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
113 |
+
__pypackages__/
|
114 |
+
|
115 |
+
# Celery stuff
|
116 |
+
celerybeat-schedule
|
117 |
+
celerybeat.pid
|
118 |
+
|
119 |
+
# SageMath parsed files
|
120 |
+
*.sage.py
|
121 |
+
|
122 |
+
# Environments
|
123 |
+
.env
|
124 |
+
.venv
|
125 |
+
env/
|
126 |
+
venv/
|
127 |
+
ENV/
|
128 |
+
env.bak/
|
129 |
+
venv.bak/
|
130 |
+
|
131 |
+
# Spyder project settings
|
132 |
+
.spyderproject
|
133 |
+
.spyproject
|
134 |
+
|
135 |
+
# Rope project settings
|
136 |
+
.ropeproject
|
137 |
+
|
138 |
+
# mkdocs documentation
|
139 |
+
/site
|
140 |
+
|
141 |
+
# mypy
|
142 |
+
.mypy_cache/
|
143 |
+
.dmypy.json
|
144 |
+
dmypy.json
|
145 |
+
|
146 |
+
# Pyre type checker
|
147 |
+
.pyre/
|
148 |
+
|
149 |
+
# pytype static type analyzer
|
150 |
+
.pytype/
|
151 |
+
|
152 |
+
# Cython debug symbols
|
153 |
+
cython_debug/
|
154 |
+
|
155 |
+
# PyCharm
|
156 |
+
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
157 |
+
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
158 |
+
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
159 |
+
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
160 |
+
#.idea/
|
161 |
+
|
162 |
+
.git/
|
163 |
+
.vscode/
|
164 |
+
.chroma/
|
165 |
+
vectorstore/
|
app.py
CHANGED
@@ -14,14 +14,9 @@ import pinecone
|
|
14 |
import streamlit as st
|
15 |
import shutil
|
16 |
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
# Set up Pinecone env
|
21 |
-
PINECONE_API_KEY = os.environ['PINECONE_API_KEY']
|
22 |
-
PINECONE_API_ENV = os.environ['PINECONE_API_ENV']
|
23 |
-
pinecone.init(api_key=PINECONE_API_KEY, environment=PINECONE_API_ENV)
|
24 |
-
|
25 |
pinecone_index_name = ''
|
26 |
chroma_collection_name = ''
|
27 |
persist_directory = ''
|
@@ -128,38 +123,44 @@ def get_response(query, chat_history):
|
|
128 |
return result['answer'], result['source_documents']
|
129 |
|
130 |
|
131 |
-
def setup_em_llm(OPENAI_API_KEY):
|
132 |
# Set up OpenAI embeddings
|
133 |
embeddings = OpenAIEmbeddings(openai_api_key=OPENAI_API_KEY)
|
134 |
# Use Open AI LLM with gpt-3.5-turbo.
|
135 |
# Set the temperature to be 0 if you do not want it to make up things
|
136 |
-
llm = ChatOpenAI(temperature=
|
137 |
openai_api_key=OPENAI_API_KEY)
|
138 |
return embeddings, llm
|
139 |
|
140 |
|
141 |
# Get user input of whether to use Pinecone or not
|
142 |
-
col1, col2, col3
|
143 |
# create the radio buttons and text input fields
|
144 |
with col1:
|
145 |
-
r_pinecone = st.radio('
|
146 |
-
with col2:
|
147 |
r_ingest = st.radio(
|
148 |
-
'
|
149 |
-
with
|
150 |
OPENAI_API_KEY = st.text_input(
|
151 |
-
"
|
152 |
-
|
|
|
|
|
153 |
if OPENAI_API_KEY:
|
154 |
-
embeddings, llm = setup_em_llm(OPENAI_API_KEY)
|
155 |
-
if r_pinecone.lower() == 'yes'
|
156 |
use_pinecone = True
|
157 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
158 |
else:
|
159 |
use_pinecone = False
|
160 |
chroma_collection_name = st.text_input(
|
161 |
-
'''
|
162 |
-
Using Chroma. Enter Chroma collection name of 3-63 characters:''')
|
163 |
persist_directory = "./vectorstore"
|
164 |
|
165 |
if pinecone_index_name or chroma_collection_name:
|
@@ -190,7 +191,6 @@ if docsearch_ready:
|
|
190 |
if query:
|
191 |
# Generate a reply based on the user input and chat history
|
192 |
reply, source = get_response(query, chat_history)
|
193 |
-
print(chat_history)
|
194 |
# Update the chat history with the user input and system response
|
195 |
chat_history.append(('User', query))
|
196 |
chat_history.append(('Bot', reply))
|
@@ -199,7 +199,7 @@ if docsearch_ready:
|
|
199 |
st.text_area('Chat record:', value=chat_history_str, height=250)
|
200 |
# Display sources
|
201 |
for i, source_i in enumerate(source):
|
202 |
-
if i <
|
203 |
if len(source_i.page_content) > 400:
|
204 |
page_content = source_i.page_content[:400]
|
205 |
else:
|
|
|
14 |
import streamlit as st
|
15 |
import shutil
|
16 |
|
17 |
+
OPENAI_API_KEY = ''
|
18 |
+
PINECONE_API_KEY = ''
|
19 |
+
PINECONE_API_ENV = ''
|
|
|
|
|
|
|
|
|
|
|
20 |
pinecone_index_name = ''
|
21 |
chroma_collection_name = ''
|
22 |
persist_directory = ''
|
|
|
123 |
return result['answer'], result['source_documents']
|
124 |
|
125 |
|
126 |
+
def setup_em_llm(OPENAI_API_KEY, temperature):
|
127 |
# Set up OpenAI embeddings
|
128 |
embeddings = OpenAIEmbeddings(openai_api_key=OPENAI_API_KEY)
|
129 |
# Use Open AI LLM with gpt-3.5-turbo.
|
130 |
# Set the temperature to be 0 if you do not want it to make up things
|
131 |
+
llm = ChatOpenAI(temperature=temperature, model_name="gpt-3.5-turbo", streaming=True,
|
132 |
openai_api_key=OPENAI_API_KEY)
|
133 |
return embeddings, llm
|
134 |
|
135 |
|
136 |
# Get user input of whether to use Pinecone or not
|
137 |
+
col1, col2, col3 = st.columns([1, 1, 1])
|
138 |
# create the radio buttons and text input fields
|
139 |
with col1:
|
140 |
+
r_pinecone = st.radio('Use Pinecone?', ('Yes', 'No'))
|
|
|
141 |
r_ingest = st.radio(
|
142 |
+
'Ingest file(s)?', ('Yes', 'No'))
|
143 |
+
with col2:
|
144 |
OPENAI_API_KEY = st.text_input(
|
145 |
+
"OpenAI API key:", type="password")
|
146 |
+
temperature = st.slider('Temperature', 0.0, 1.0, 0.1)
|
147 |
+
k_sources = st.slider('# source(s) to print out', 0, 20, 2)
|
148 |
+
with col3:
|
149 |
if OPENAI_API_KEY:
|
150 |
+
embeddings, llm = setup_em_llm(OPENAI_API_KEY, temperature)
|
151 |
+
if r_pinecone.lower() == 'yes':
|
152 |
use_pinecone = True
|
153 |
+
PINECONE_API_KEY = st.text_input(
|
154 |
+
"Pinecone API key:", type="password")
|
155 |
+
PINECONE_API_ENV = st.text_input(
|
156 |
+
"Pinecone API env:", type="password")
|
157 |
+
pinecone_index_name = st.text_input('Pinecone index:')
|
158 |
+
pinecone.init(api_key=PINECONE_API_KEY,
|
159 |
+
environment=PINECONE_API_ENV)
|
160 |
else:
|
161 |
use_pinecone = False
|
162 |
chroma_collection_name = st.text_input(
|
163 |
+
'''Chroma collection name of 3-63 characters:''')
|
|
|
164 |
persist_directory = "./vectorstore"
|
165 |
|
166 |
if pinecone_index_name or chroma_collection_name:
|
|
|
191 |
if query:
|
192 |
# Generate a reply based on the user input and chat history
|
193 |
reply, source = get_response(query, chat_history)
|
|
|
194 |
# Update the chat history with the user input and system response
|
195 |
chat_history.append(('User', query))
|
196 |
chat_history.append(('Bot', reply))
|
|
|
199 |
st.text_area('Chat record:', value=chat_history_str, height=250)
|
200 |
# Display sources
|
201 |
for i, source_i in enumerate(source):
|
202 |
+
if i < k_sources:
|
203 |
if len(source_i.page_content) > 400:
|
204 |
page_content = source_i.page_content[:400]
|
205 |
else:
|
tmp_docs/empty.txt
DELETED
File without changes
|