Upload 9 files

.gitignore

@@ -0,0 +1,161 @@
+# Byte-compiled / optimized / DLL files
+cacert.pem
+__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/

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Marsiya Issah 
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

Pipfile

@@ -0,0 +1,20 @@
+[[source]]
+url = "https://pypi.org/simple"
+verify_ssl = true
+name = "pypi"
+
+[packages]
+openai = "*"
+langchain = "*"
+streamlit = "*"
+python-dotenv = "*"
+langchain-community = "*"
+langchain-openai = "*"
+sentence-transformers = "*"
+chromadb = "*"
+nest-asyncio = "*"
+
+[dev-packages]
+
+[requires]
+python_version = "3.10"

main.py

@@ -0,0 +1,49 @@
+import os
+import asyncio
+from langchain.document_loaders.sitemap import SitemapLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings.sentence_transformer import SentenceTransformerEmbeddings
+from langchain_community.vectorstores import Chroma
+import streamlit as st
+
+
+os.environ.get("HUGGINGFACEHUB_API_TOKEN")
+
+#Function to fetch data from website
+#https://python.langchain.com/docs/modules/data_connection/document_loaders/integrations/sitemap
+def get_website_data(sitemap_url):
+    loop = asyncio.new_event_loop()
+    asyncio.set_event_loop(loop)
+    loader = SitemapLoader(sitemap_url)
+    loader.requests_kwargs = {'verify': './cacert.pem'}
+    docs = loader.load()
+    # print(docs)
+    return docs
+
+#Function to split data into smaller chunks
+def split_data(docs):
+    text_splitter = RecursiveCharacterTextSplitter(
+    chunk_size = 1000,
+    chunk_overlap  = 200,
+    length_function = len,
+    )
+    docs_chunks = text_splitter.split_documents(docs)
+    # print(docs_chunks)
+    return docs_chunks
+
+#Function to create embeddings instance
+def create_embeddings():
+    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+    return embeddings
+
+# Function to push data to Chroma
+def push_to_chroma(embeddings, chunk_data):
+    Chroma.from_documents(chunk_data, embeddings, persist_directory="./chroma_db")
+
+# Function to pull data from chroma
+def pull_from_chroma(query):
+    db = Chroma(persist_directory="./chroma_db", embedding_function= create_embeddings())
+    docs = db.similarity_search(query)
+    return docs
+
+

requirements.txt

@@ -0,0 +1,7 @@
+openai
+langchain
+streamlit
+langchain-experimental
+langchain-community
+sentence-transformers
+chromadb

streamlit.py

@@ -0,0 +1,72 @@
+import streamlit as st
+from main import *
+
+
+if __name__ == "__main__":
+     st.set_page_config(page_title="AI Assistant",
+                              page_icon='🤖',
+                              layout='centered')
+
+     st.markdown("<h3 style='text-align: center;'>🤖 JOB Website AI Assistance</h3>", unsafe_allow_html=True)
+
+     # Creating Session State Variable
+     if 'HuggingFace_API_Key' not in st.session_state:
+          st.session_state['HuggingFace_API_Key'] =''
+
+     #********SIDE BAR*******
+     with st.sidebar:
+          st.sidebar.title("🗝️")
+          st.session_state['HuggingFace_API_Key']= st.text_input("What's your HuggingFace API key?",type="password")
+          load_button = st.button("Load", key="load_button")
+
+     if load_button:
+          #Proceed only if API keys are provided
+          if st.session_state['HuggingFace_API_Key'] !="":
+               if os.path.exists('./chroma_db'):
+                    st.sidebar.success("Data pushed to Chromadb successfully!")
+               else:
+                    #Fetch data from site
+                    site_data= get_website_data("https://jobs.apple.com/sitemap/sitemap-jobs-en-gb.xml")
+                    st.toast("Data pull done...", icon='😍')
+
+                    #Split data into chunks
+                    chunks_data=split_data(site_data)
+                    st.toast("Spliting data done...", icon='🔥')
+
+                    #Creating embeddings instance
+                    embeddings=create_embeddings()
+                    st.toast("Embeddings instance creation done...",icon='🤖')
+
+                    #Push data to Chroma
+                    db = push_to_chroma(embeddings,chunks_data)
+                    st.toast("Pushing data to Chromadb done...")
+                    st.sidebar.success("Data pushed to Chromadb successfully!")
+          else:
+               st.sidebar.error("Ooopssss!!! Please provide API key.....")
+
+
+     prompt = st.text_input('Enter keyword - e.g Job title',key="prompt")  # The box for the text prompt
+     document_count = st.slider('No.Of links to return 🔗 - (0 LOW || 5 HIGH)', 0, 5, 2,step=1)
+
+     # submit = st.button("Search")
+
+     with st.spinner("Searching..."):
+        if st.button("Search"):
+          #Pull index data from Chroma
+          relavant_docs = pull_from_chroma(prompt)
+          st.toast("Chroma index retrieval done...")
+          # st.write(relavant_docs)
+     if prompt:
+          if not load_button:
+               if st.session_state['HuggingFace_API_Key'] !="":
+                    #Displaying search results
+                    st.success("Please find the search results :")
+                    for index in range(min(document_count, len(relavant_docs))):
+                         document = relavant_docs[index]
+                         st.write("👉**Result : " + str(index + 1) + "**")
+                         st.write("**Info**: " + document.page_content)
+                         st.write("**Link**: " + document.metadata['source'])
+                         st.markdown("-----------------------------------------------------------------------")
+               else:
+                    st.sidebar.error("Ooopssss!!! Please provide API key.....")
+