add everything

.gitignore

@@ -0,0 +1,161 @@
+.DS_Store
+# 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/

app.py

@@ -0,0 +1,61 @@
+from langchain_community.document_loaders import HuggingFaceDatasetLoader
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+from transformers import pipeline
+import gradio as gr
+import os
+from dotenv import load_dotenv, find_dotenv
+
+_ = load_dotenv(find_dotenv()) # read local .env file
+hf_api_key = os.environ['HF_TOKEN']
+
+# Load the data
+loader = HuggingFaceDatasetLoader(path="HuggingFaceH4/CodeAlpaca_20K", page_content_column="completion", use_auth_token=hf_api_key)
+data = loader.load()
+
+# Document Transformers
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=150)
+docs = text_splitter.split_documents(data)
+
+# Text Embedding
+embeddings = HuggingFaceEmbeddings(
+    model_name="sentence-transformers/all-MiniLM-l6-v2",
+    model_kwargs={'device':'cpu'},
+    encode_kwargs={'normalize_embeddings': False}
+)
+
+# Set up Vector Stores
+db = FAISS.from_documents(docs, embeddings)
+
+# Set up retrievers
+retriever = db.as_retriever(search_kwargs={"k": 4})
+
+txt2txt_gen = pipeline("text2text-generation", model="Salesforce/codet5-base")
+
+def generate(question):
+    docs = retriever.get_relevant_documents(question)
+    context = docs[0].page_content
+    input = f"question: {question} context: {context}"
+    output = txt2txt_gen(input)
+    return output[0]['generated_text']
+
+
+def respond(message, chat_history):
+    bot_message = generate(message)
+    chat_history.append((message, bot_message))
+    
+    return "", chat_history
+
+# Set up the chat interface
+with gr.Blocks() as demo:
+    chatbot = gr.Chatbot(height=240) #just to fit the notebook
+    msg = gr.Textbox(label="Ask away")
+    btn = gr.Button("Submit")
+    clear = gr.ClearButton(components=[msg, chatbot], value="Clear console")
+
+    btn.click(respond, inputs=[msg, chatbot], outputs=[msg, chatbot])
+    msg.submit(respond, inputs=[msg, chatbot], outputs=[msg, chatbot]) #Press enter to submit
+
+demo.queue().launch()

requirements.txt

@@ -0,0 +1,9 @@
+langchain 
+langchain-community
+torch 
+transformers[torch] 
+sentence-transformers 
+datasets 
+faiss-cpu 
+gradio
+python-dotenv