Upload 10 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 +1,22 @@
+[[source]]
+url = "https://pypi.org/simple"
+verify_ssl = true
+name = "pypi"
+
+[packages]
+openai = "*"
+langchain = "*"
+streamlit = "*"
+python-dotenv = "*"
+langchain-community = "*"
+langchain-openai = "*"
+sentence-transformers = "*"
+pypdf = "*"
+tiktoken = "*"
+lancedb = "*"
+bs4 = "*"
+
+[dev-packages]
+
+[requires]
+python_version = "3.10"

README.md

@@ -1,13 +1,12 @@
----
-title: Hr Screening
-emoji: ⚡
-colorFrom: purple
-colorTo: blue
-sdk: streamlit
-sdk_version: 1.30.0
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+### HR - Resume Screening Assistance
+
+LangChain | Streamlit | LanceDB | Openai | load_summarize_chain
+
+![App](app.png)
+
+## To run this app locally, follow these steps:
+
+- Clone the repository
+- `pipenv shell`
+- `pipenv install -r requirement.txt`
+- `streamlit run streamlit.py`

requirements.txt

@@ -0,0 +1,8 @@
+openai
+langchain
+streamlit
+langchain-community
+sentence-transformers
+tiktoken
+python-dotenv
+pinecone-client

streamlit.py

@@ -0,0 +1,67 @@
+import streamlit as st
+from dotenv import load_dotenv
+from utils import *
+import uuid
+
+#Creating session variables
+if 'unique_id' not in st.session_state:
+    st.session_state['unique_id'] =''
+
+def main():
+    load_dotenv()
+
+    st.set_page_config(page_title="Resume Screening Assistance", page_icon="📝")
+    st.title("HR - Resume Screening Assistance...")
+    # st.subheader("I can help you in resume screening process")
+
+    job_description = st.text_area("Please paste the 'JOB DESCRIPTION' here...", key="desc")
+    document_count = st.text_input("Enter the no.of resumes to return",key="count")
+    # Upload the Resumes (pdf files)
+    pdf = st.file_uploader("Upload resumes here, only PDF files allowed", type=["pdf"], accept_multiple_files=True)
+
+    submit=st.button("Screen")
+
+    if submit:
+        with st.spinner('Wait for it...'):
+
+            #Creating a unique ID, so that we can use to query and get only the user uploaded documents from PINECONE vector store
+            st.session_state['unique_id']=uuid.uuid4().hex
+
+            #Create a documents list out of all the user uploaded pdf files
+            final_docs_list=create_docs(pdf,st.session_state['unique_id'])
+
+            #Displaying the count of resumes that have been uploaded
+            st.write("*Resumes uploaded* :"+str(len(final_docs_list)))
+
+            #Create embeddings instance
+            embeddings=create_embeddings_load_data()
+
+            #Push data to PINECONE
+            # using already created index automatic-ticket-tool
+            table = push_to_lancedb(embeddings)
+
+            #Fecth relavant documents from LanceDB
+            relavant_docs = similar_docs_lancedb(job_description,table,embeddings,final_docs_list)
+
+            #st.write(relavant_docs)
+
+            #Introducing a line separator
+            st.write(":heavy_minus_sign:" * 30)
+            st.success(f"Find below the {document_count} Resumes")
+
+            # For each item in relavant docs - we are displaying some info of it on the UI
+            for idx, resume in enumerate(relavant_docs[:int(document_count)]):
+                st.subheader("👉 Resume "+str(idx+1))
+                # st.write(resume.page_content)
+
+                #Gets the summary of the current item using 'get_summary' function that we have created which uses LLM & Langchain chain
+                summary = get_summary(relavant_docs[idx])
+                print([relavant_docs[idx]])
+                st.write("**Summary** : "+summary)
+
+        st.success("Hope I was able to save your time❤️")
+
+
+#Invoking main function
+if __name__ == '__main__':
+    main()

utils.py

@@ -0,0 +1,79 @@
+from langchain.vectorstores import LanceDB, Pinecone as pc
+from langchain.llms import OpenAI
+from langchain.embeddings.sentence_transformer import SentenceTransformerEmbeddings
+from langchain.schema import Document
+from pypdf import PdfReader
+from langchain.llms.openai import OpenAI
+from langchain.chains.summarize import load_summarize_chain
+from langchain.llms import HuggingFaceHub
+import lancedb
+
+
+#Extract Information from PDF file
+def get_pdf_text(pdf_doc):
+    text = ""
+    pdf_reader = PdfReader(pdf_doc)
+    for page in pdf_reader.pages:
+        text += page.extract_text()
+    return text
+
+
+
+# iterate over files in
+# that user uploaded PDF files, one by one
+def create_docs(user_pdf_list, unique_id):
+    docs=[]
+    # each pdf file is a doc. We are creating our own Document with it
+    for filename in user_pdf_list:
+
+        chunks=get_pdf_text(filename)
+
+        #Adding items to our list - Adding data & its metadata
+        docs.append(Document(
+            page_content=chunks,
+            metadata={"name": filename.name,"id":filename.file_id,"type=":filename.type,"size":filename.size,"unique_id":unique_id},
+        ))
+
+    return docs # Document chunks list
+
+
+#Create embeddings instance
+def create_embeddings_load_data():
+    #embeddings = OpenAIEmbeddings()
+    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+    return embeddings
+
+# push to lancedb
+def push_to_lancedb(embeddings):
+    db = lancedb.connect("/lancedb")
+    # sample data which will be overwritten when ne dos are uploaded
+    table = db.create_table(
+        "resumes",
+        data=[
+            {
+                "vector": embeddings.embed_query("Hello World"),
+                "text": "Hello World",
+                "id": "1",
+            }
+        ],
+        mode="overwrite",
+    )
+    return table
+
+def pull_from_lancedb(table, embeddings, docs):
+    docsearch = LanceDB.from_documents(documents=docs, embedding = embeddings, connection=table)
+    return docsearch
+
+def similar_docs_lancedb(query, table, embeddings, docs):
+  docsearch = pull_from_lancedb(table, embeddings, docs)
+  similar_docs = docsearch.similarity_search(query)
+  return similar_docs
+
+
+# Helps us get the summary of a document
+def get_summary(current_doc):
+    llm = OpenAI(temperature=0)
+    #llm = HuggingFaceHub(repo_id="bigscience/bloom", model_kwargs={"temperature":1e-10})
+    chain = load_summarize_chain(llm, chain_type="map_reduce")
+    summary = chain.run([current_doc])
+    return summary