chat1

.gitignore

@@ -0,0 +1,160 @@
+# 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/

README.md

@@ -4,7 +4,7 @@ emoji: 👀
 colorFrom: indigo
 colorTo: indigo
 sdk: gradio
-sdk_version: 3.38.0
+sdk_version: 3.11.0
 app_file: app.py
 pinned: false
 license: apache-2.0

app.ipynb

@@ -0,0 +1,216 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import datetime\n",
+    "import gradio as gr\n",
+    "from dotenv import load_dotenv\n",
+    "from langchain.vectorstores import Chroma\n",
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.chains import RetrievalQA\n",
+    "from langchain.chains import ConversationalRetrievalChain\n",
+    "from langchain.memory import ConversationBufferMemory\n",
+    "\n",
+    "\n",
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# from langchain.memory import MemoryViewMemory\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "gpt-3.5-turbo-0301\n"
+     ]
+    }
+   ],
+   "source": [
+    "import datetime\n",
+    "current_date = datetime.datetime.now().date()\n",
+    "if current_date < datetime.date(2023, 9, 2):\n",
+    "    llm_name = \"gpt-3.5-turbo-0301\"\n",
+    "else:\n",
+    "    llm_name = \"gpt-3.5-turbo\"\n",
+    "print(llm_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def chatWithNCAIR(question, history):\n",
+    "    load_dotenv()\n",
+    "\n",
+    "    persist_directory = 'docs/chroma/'\n",
+    "    embedding = OpenAIEmbeddings()\n",
+    "    vectordb = Chroma(persist_directory=persist_directory, embedding_function=embedding)\n",
+    "    llm = ChatOpenAI(model_name=llm_name, temperature=0)\n",
+    "\n",
+    "    template = \"\"\"Use the following pieces of context to answer the question at the end. \n",
+    "    If you don't know the answer, just say that you don't know, don't try to make up an answer. \n",
+    "    Use three sentences maximum. Keep the answer as concise as possible. \n",
+    "    Always say \"thank you for choosing NCAIR BOT!\" at the end of the answer. \n",
+    "    {context}\n",
+    "    Question: {question}\n",
+    "    Helpful Answer:\"\"\"\n",
+    "    QA_CHAIN_PROMPT = PromptTemplate(input_variables=[\"context\", \"question\"],template=template,)\n",
+    "\n",
+    "    # Run chain\n",
+    "    from langchain.chains import RetrievalQA\n",
+    "    # question = \"Will interns go through the fabLab during the onboarding?\"\n",
+    "    qa_chain = RetrievalQA.from_chain_type(llm,\n",
+    "        retriever=vectordb.as_retriever(),\n",
+    "        return_source_documents=True,\n",
+    "        chain_type_kwargs={\"prompt\": QA_CHAIN_PROMPT})\n",
+    "\n",
+    "    memory = ConversationBufferMemory(\n",
+    "    memory_key=\"chat_history\",\n",
+    "    return_messages=True\n",
+    "    )\n",
+    "    retriever=vectordb.as_retriever()\n",
+    "    qa = ConversationalRetrievalChain.from_llm(\n",
+    "    llm,\n",
+    "    retriever=retriever,\n",
+    "    memory=memory\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "    result = qa({\"question\": question})\n",
+    "    return result[\"answer\"]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Yes, as an intern in NCAIR, you will first undergo the onboarding session in Fablab, PCB, shopbot, 3D printing, solid work, and then go through compulsory NADIT programs.'"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chatWithNCAIR(\"Will interns go through the fabLab during the onboarding?\",\"\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# chatWithNCAIR(\"Is it compulsory?\",\"\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ! pip install --upgrade gradio"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running on local URL:  http://127.0.0.1:7860\n",
+      "Running on public URL: https://0e3e0326bf1f8474c9.gradio.live\n",
+      "\n",
+      "This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"https://0e3e0326bf1f8474c9.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "demo = gr.ChatInterface(fn=chatWithNCAIR,\n",
+    "    chatbot=gr.Chatbot(height=300, min_width=40),\n",
+    "    textbox=gr.Textbox(placeholder=\"Ask me a question relating to NCAIR\"),\n",
+    "    title=\"Chat with NCAIR💬\",\n",
+    "    description=\"Ask NCAIR any question\",\n",
+    "    theme=\"soft\",\n",
+    "    cache_examples=True,\n",
+    "    retry_btn=None,\n",
+    "    undo_btn=\"Delete Previous\",\n",
+    "    clear_btn=\"Clear\",)\n",
+    "\n",
+    "demo.launch(share=True)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.8"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

app.py

@@ -0,0 +1,78 @@
+import datetime
+import gradio as gr
+from dotenv import load_dotenv
+from langchain.vectorstores import Chroma
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.chat_models import ChatOpenAI
+from langchain.prompts import PromptTemplate
+from langchain.chains import RetrievalQA
+from langchain.chains import ConversationalRetrievalChain
+from langchain.memory import ConversationBufferMemory
+
+
+import warnings
+warnings.filterwarnings('ignore')
+
+current_date = datetime.datetime.now().date()
+if current_date < datetime.date(2023, 9, 2):
+    llm_name = "gpt-3.5-turbo-0301"
+else:
+    llm_name = "gpt-3.5-turbo"
+# print(llm_name)
+
+
+def chatWithNCAIR(question, history):
+    load_dotenv()
+
+    persist_directory = 'docs/chroma/'
+    embedding = OpenAIEmbeddings()
+    vectordb = Chroma(persist_directory=persist_directory,
+                      embedding_function=embedding)
+    llm = ChatOpenAI(model_name=llm_name, temperature=0)
+
+    template = """Use the following pieces of context to answer the question at the end. 
+    If you don't know the answer, just say that you don't know, don't try to make up an answer. 
+    Use three sentences maximum. Keep the answer as concise as possible. 
+    Always say "thank you for choosing NCAIR BOT!" at the end of the answer. 
+    {context}
+    Question: {question}
+    Helpful Answer:"""
+    QA_CHAIN_PROMPT = PromptTemplate(
+        input_variables=["context", "question"], template=template,)
+
+    # Run chain
+    from langchain.chains import RetrievalQA
+    # question = "Will interns go through the fabLab during the onboarding?"
+    qa_chain = RetrievalQA.from_chain_type(llm,
+                                           retriever=vectordb.as_retriever(),
+                                           return_source_documents=True,
+                                           chain_type_kwargs={"prompt": QA_CHAIN_PROMPT})
+
+    memory = ConversationBufferMemory(
+        memory_key="chat_history",
+        return_messages=True
+    )
+    retriever = vectordb.as_retriever()
+    qa = ConversationalRetrievalChain.from_llm(
+        llm,
+        retriever=retriever,
+        memory=memory
+    )
+
+    result = qa({"question": question})
+    return result["answer"]
+
+
+demo = gr.ChatInterface(fn=chatWithNCAIR,
+                        chatbot=gr.Chatbot(height=300, min_width=40),
+                        textbox=gr.Textbox(
+                            placeholder="Ask me a question relating to NCAIR"),
+                        title="Chat with NCAIR💬",
+                        description="Ask NCAIR any question",
+                        theme="soft",
+                        cache_examples=True,
+                        retry_btn=None,
+                        undo_btn="Delete Previous",
+                        clear_btn="Clear",)
+
+demo.launch(inline=False)

docs/chroma/chroma-collections.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0d400379140f0334717afd5ded1e939056093dcddd99f8d04303d7b4a02c829
+size 557

docs/chroma/chroma-embeddings.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d68c750aa538c7a2c358f48f8753a8cdaf5818a3490d220773979d55b72f268
+size 1696701

docs/chroma/index/id_to_uuid_e9f84229-87ab-426e-a3d7-e7ec6f6f5d41.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d3c04482c0178c82187bc551504affad306d4393dd174574a496362edd7e9c
+size 4245

docs/chroma/index/index_e9f84229-87ab-426e-a3d7-e7ec6f6f5d41.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb3e967edc62e77b399c78f0cc8e880cbed7747e6f9687cb6b5670f401c2898f
+size 843572

docs/chroma/index/index_metadata_e9f84229-87ab-426e-a3d7-e7ec6f6f5d41.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c53793715df10b935e9b52ece240f4e042b4e862360889b585a4beb084dfc91
+size 103

docs/chroma/index/uuid_to_id_e9f84229-87ab-426e-a3d7-e7ec6f6f5d41.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45bca60c0cc265ca0df973a335e615317e610b0f352bb139209431f233f2193c
+size 4974

requirements.txt

@@ -0,0 +1,11 @@
+typing
+typing-inspect
+typing_extensions
+openai
+langchain
+chroma
+chromadb
+pydantic
+python-dotenv
+gradio
+datetime