updated UI

.gitignore

@@ -0,0 +1,165 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+.git/
+.vscode/
+.chroma/
+vectorstore/

app.py

@@ -14,14 +14,9 @@ import pinecone
 import streamlit as st
 import shutil
 
-# Set up OpenAI API key (from .bashrc, Windows environment variables, .env)
-OPENAI_API_KEY = os.environ['OPENAI_API_KEY']
-
-# Set up Pinecone env
-PINECONE_API_KEY = os.environ['PINECONE_API_KEY']
-PINECONE_API_ENV = os.environ['PINECONE_API_ENV']
-pinecone.init(api_key=PINECONE_API_KEY, environment=PINECONE_API_ENV)
-
+OPENAI_API_KEY = ''
+PINECONE_API_KEY = ''
+PINECONE_API_ENV = ''
 pinecone_index_name = ''
 chroma_collection_name = ''
 persist_directory = ''
@@ -128,38 +123,44 @@ def get_response(query, chat_history):
     return result['answer'], result['source_documents']
 
 
-def setup_em_llm(OPENAI_API_KEY):
+def setup_em_llm(OPENAI_API_KEY, temperature):
     # Set up OpenAI embeddings
     embeddings = OpenAIEmbeddings(openai_api_key=OPENAI_API_KEY)
     # Use Open AI LLM with gpt-3.5-turbo.
     # Set the temperature to be 0 if you do not want it to make up things
-    llm = ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo", streaming=True,
+    llm = ChatOpenAI(temperature=temperature, model_name="gpt-3.5-turbo", streaming=True,
                      openai_api_key=OPENAI_API_KEY)
     return embeddings, llm
 
 
 # Get user input of whether to use Pinecone or not
-col1, col2, col3, col4 = st.columns([1, 1, 1, 1])
+col1, col2, col3 = st.columns([1, 1, 1])
 # create the radio buttons and text input fields
 with col1:
-    r_pinecone = st.radio('Do you want to use Pinecone index?', ('Yes', 'No'))
-with col2:
+    r_pinecone = st.radio('Use Pinecone?', ('Yes', 'No'))
     r_ingest = st.radio(
-        'Do you want to ingest the file(s)?', ('Yes', 'No'))
-with col3:
+        'Ingest file(s)?', ('Yes', 'No'))
+with col2:
     OPENAI_API_KEY = st.text_input(
-        "Enter your OpenAI API key and press Enter", type="password")
-with col4:
+        "OpenAI API key:", type="password")
+    temperature = st.slider('Temperature', 0.0, 1.0, 0.1)
+    k_sources = st.slider('# source(s) to print out', 0, 20, 2)
+with col3:
     if OPENAI_API_KEY:
-        embeddings, llm = setup_em_llm(OPENAI_API_KEY)
-        if r_pinecone.lower() == 'yes' and PINECONE_API_KEY != '':
+        embeddings, llm = setup_em_llm(OPENAI_API_KEY, temperature)
+        if r_pinecone.lower() == 'yes':
             use_pinecone = True
-            pinecone_index_name = st.text_input('Enter your Pinecone index')
+            PINECONE_API_KEY = st.text_input(
+                "Pinecone API key:", type="password")
+            PINECONE_API_ENV = st.text_input(
+                "Pinecone API env:", type="password")
+            pinecone_index_name = st.text_input('Pinecone index:')
+            pinecone.init(api_key=PINECONE_API_KEY,
+                          environment=PINECONE_API_ENV)
         else:
             use_pinecone = False
             chroma_collection_name = st.text_input(
-                '''Not using Pinecone or empty Pinecone API key provided. 
-                Using Chroma. Enter Chroma collection name of 3-63 characters:''')
+                '''Chroma collection name of 3-63 characters:''')
             persist_directory = "./vectorstore"
 
 if pinecone_index_name or chroma_collection_name:
@@ -190,7 +191,6 @@ if docsearch_ready:
     if query:
         # Generate a reply based on the user input and chat history
         reply, source = get_response(query, chat_history)
-        print(chat_history)
         # Update the chat history with the user input and system response
         chat_history.append(('User', query))
         chat_history.append(('Bot', reply))
@@ -199,7 +199,7 @@ if docsearch_ready:
         st.text_area('Chat record:', value=chat_history_str, height=250)
         # Display sources
         for i, source_i in enumerate(source):
-            if i < 2:
+            if i < k_sources:
                 if len(source_i.page_content) > 400:
                     page_content = source_i.page_content[:400]
                 else: