Upload gradio app (manual upload)

.gitignore

@@ -0,0 +1,22 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# ignore all jupyter notebooks
+# *.ipynb
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# select scripts
+.chroma/
+chromadb_bul_details/
+chromadb_food_guide/
+
+
+.env
+
+optimizer.pt
+# pytorch_model.bin
+
+*.bin

Untitled.ipynb

@@ -0,0 +1,502 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "c031ebee-371a-4ffd-bb4b-8ee273a5dfc2",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "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\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "import openai\n",
+    "from dotenv import load_dotenv\n",
+    "load_dotenv()\n",
+    "\n",
+    "print(os.getenv(\"OPENAI_API_KEY\"))\n",
+    "openai.api_key = os.getenv(\"OPENAI_API_KEY\")\n",
+    "\n",
+    "from langchain import PromptTemplate\n",
+    "from langchain.chains import RetrievalQA\n",
+    "\n",
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.text_splitter import MarkdownTextSplitter\n",
+    "from langchain.vectorstores import Chroma\n",
+    "from langchain.document_loaders import TextLoader\n",
+    "\n",
+    "from langchain.agents import Tool\n",
+    "from langchain.memory import ConversationBufferMemory\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.utilities import SerpAPIWrapper\n",
+    "from langchain.agents import initialize_agent\n",
+    "from langchain.agents import AgentType\n",
+    "from langchain.vectorstores import FAISS\n",
+    "\n",
+    "from langchain.chains.router import MultiRetrievalQAChain\n",
+    "from langchain.llms import OpenAI\n",
+    "\n",
+    "REST_PERSIST_DIRECTORY = \"chromadb_bul_details\"\n",
+    "FOOD_GUIDE_PERSIST_DIRECTORY = \"chromadb_food_guide\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "e5f08445-3da2-4f1d-8b6f-624200cc77c2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = OpenAIEmbeddings()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "0db17fe4-0fe8-47f3-9626-8f31039859cd",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "No embedding_function provided, using default embedding function: DefaultEmbeddingFunction https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2\n"
+     ]
+    }
+   ],
+   "source": [
+    "bulevar_restaurant_texts = [\n",
+    "    \"Bulevar is open Sunday through Wednesday from 5-9pm, and Thursday through Saturday from 4-10pm. It is open for lunch on Friday from 11-3pm\",\n",
+    "    \"Bulevar is located in the Arboretum at 360 and Mopac, next to Eddie V's\",\n",
+    "    \"Bulevar is an excellent Mexican Cuisine restaurant with a laid back style to fine-dining.\",\n",
+    "    \"Bulevar is another restaurant created by Guy and Larry. With the success of their ATX Cocina, Bulevar has created another unique dining experience with high quality dishes.\"\n",
+    "]\n",
+    "bulevar_details_retriever = Chroma.from_texts(bulevar_restaurant_texts, persist_directory=REST_PERSIST_DIRECTORY, embedding_function=embeddings)\n",
+    "bulevar_details_retriever.persist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "ebf95554-2bf8-4665-a93a-9e033af54a64",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "loader = TextLoader('raw_text/food_guide.md')\n",
+    "documents = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "55add9c5-cef1-4106-a9f8-560228d2c5ea",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "text_splitter = MarkdownTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "docs = text_splitter.split_documents(documents)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "fffe2d0b-d1c9-453f-99b1-bad54b6c5614",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(page_content='## BONE-IN RIBEYE\\n\\n**<span style=\"text-decoration:underline;\">Chef Description:</span>**\\n\\nThe ribeye is carved from the primal section called the beef rib. It falls between the chuck (shoulder) and the loin, and spans from ribs six through twelve. This section of the animal naturally collects more intramuscular fat, creating the beautiful white lines of fat. Our ribeye is coming from Linz Meats out of Chicago, this cut is wet aged and hand cut, butter basted and rested. Served over a mixed animal roasted jus and with cebollitas, blistered shishitos and chipotle garlic butter. Cook time is roughly 45 minutes.\\n\\n**<span style=\"text-decoration:underline;\">Table Talk:</span>**\\n\\nOur prime wet aged ribeye is cooked over post oak wood and butter basted, served with cebollitas, shishitos & chipotle garlic butter\\n\\n**<span style=\"text-decoration:underline;\">Allergies:</span>**\\n\\nDairy,Garlic, Onion, Chilies', metadata={'source': 'raw_text/food_guide.md'})"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs[23]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "c7d314fa-d1ac-462c-ac29-1a2a2b8a53af",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "No embedding_function provided, using default embedding function: DefaultEmbeddingFunction https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2\n"
+     ]
+    }
+   ],
+   "source": [
+    "docs_retriever = Chroma.from_documents(docs, persist_directory=FOOD_GUIDE_PERSIST_DIRECTORY, embedding_function=embeddings)\n",
+    "docs_retriever.persist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "a9e35123-7cfb-4890-bbe5-e1648aaf1cca",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# docs_retriever = None\n",
+    "# bulevar_details_retriever = None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "b632b749-9e76-461a-87a8-036159d075cc",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# docs_retriever = Chroma(persist_directory=FOOD_GUIDE_PERSIST_DIRECTORY, embedding_function=embeddings)\n",
+    "# bulevar_details_retriever = Chroma(persist_directory=REST_PERSIST_DIRECTORY, embedding_function=OpenAIEmbeddings())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "a22fe6e4-434f-47aa-92bf-02d088db2d1f",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "ename": "AttributeError",
+     "evalue": "module 'chromadb.errors' has no attribute 'NotEnoughElementsException'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mInvalidDimensionException\u001b[0m                 Traceback (most recent call last)",
+      "File \u001b[0;32m~/miniconda/envs/mlops/lib/python3.10/site-packages/langchain/vectorstores/chroma.py:121\u001b[0m, in \u001b[0;36mChroma.__query_collection\u001b[0;34m(self, query_texts, query_embeddings, n_results, where, **kwargs)\u001b[0m\n\u001b[1;32m    120\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 121\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_collection\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mquery\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    122\u001b[0m \u001b[43m        \u001b[49m\u001b[43mquery_texts\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mquery_texts\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    123\u001b[0m \u001b[43m        \u001b[49m\u001b[43mquery_embeddings\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mquery_embeddings\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    124\u001b[0m \u001b[43m        \u001b[49m\u001b[43mn_results\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mi\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    125\u001b[0m \u001b[43m        \u001b[49m\u001b[43mwhere\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mwhere\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    126\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    127\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    128\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m chromadb\u001b[38;5;241m.\u001b[39merrors\u001b[38;5;241m.\u001b[39mNotEnoughElementsException:\n",
+      "File \u001b[0;32m~/miniconda/envs/mlops/lib/python3.10/site-packages/chromadb/api/models/Collection.py:230\u001b[0m, in \u001b[0;36mCollection.query\u001b[0;34m(self, query_embeddings, query_texts, n_results, where, where_document, include)\u001b[0m\n\u001b[1;32m    228\u001b[0m     where_document \u001b[38;5;241m=\u001b[39m {}\n\u001b[0;32m--> 230\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_client\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_query\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    231\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcollection_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mid\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    232\u001b[0m \u001b[43m    \u001b[49m\u001b[43mquery_embeddings\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mquery_embeddings\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    233\u001b[0m \u001b[43m    \u001b[49m\u001b[43mn_results\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mn_results\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    234\u001b[0m \u001b[43m    \u001b[49m\u001b[43mwhere\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mwhere\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    235\u001b[0m \u001b[43m    \u001b[49m\u001b[43mwhere_document\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mwhere_document\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    236\u001b[0m \u001b[43m    \u001b[49m\u001b[43minclude\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minclude\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    237\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/miniconda/envs/mlops/lib/python3.10/site-packages/chromadb/api/local.py:439\u001b[0m, in \u001b[0;36mLocalAPI._query\u001b[0;34m(self, collection_id, query_embeddings, n_results, where, where_document, include)\u001b[0m\n\u001b[1;32m    430\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_query\u001b[39m(\n\u001b[1;32m    431\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    432\u001b[0m     collection_id: UUID,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    437\u001b[0m     include: Include \u001b[38;5;241m=\u001b[39m [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdocuments\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmetadatas\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdistances\u001b[39m\u001b[38;5;124m\"\u001b[39m],\n\u001b[1;32m    438\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m QueryResult:\n\u001b[0;32m--> 439\u001b[0m     uuids, distances \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_db\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_nearest_neighbors\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    440\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcollection_uuid\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcollection_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    441\u001b[0m \u001b[43m        \u001b[49m\u001b[43mwhere\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mwhere\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    442\u001b[0m \u001b[43m        \u001b[49m\u001b[43mwhere_document\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mwhere_document\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    443\u001b[0m \u001b[43m        \u001b[49m\u001b[43membeddings\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mquery_embeddings\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    444\u001b[0m \u001b[43m        \u001b[49m\u001b[43mn_results\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mn_results\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    445\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    447\u001b[0m     include_embeddings \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124membeddings\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m include\n",
+      "File \u001b[0;32m~/miniconda/envs/mlops/lib/python3.10/site-packages/chromadb/db/clickhouse.py:591\u001b[0m, in \u001b[0;36mClickhouse.get_nearest_neighbors\u001b[0;34m(self, collection_uuid, where, where_document, embeddings, n_results)\u001b[0m\n\u001b[1;32m    590\u001b[0m index \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_index(collection_uuid)\n\u001b[0;32m--> 591\u001b[0m uuids, distances \u001b[38;5;241m=\u001b[39m \u001b[43mindex\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_nearest_neighbors\u001b[49m\u001b[43m(\u001b[49m\u001b[43membeddings\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mn_results\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mids\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    593\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m uuids, distances\n",
+      "File \u001b[0;32m~/miniconda/envs/mlops/lib/python3.10/site-packages/chromadb/db/index/hnswlib.py:272\u001b[0m, in \u001b[0;36mHnswlib.get_nearest_neighbors\u001b[0;34m(self, query, k, ids)\u001b[0m\n\u001b[1;32m    271\u001b[0m \u001b[38;5;66;03m# Check dimensionality\u001b[39;00m\n\u001b[0;32m--> 272\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_check_dimensionality\u001b[49m\u001b[43m(\u001b[49m\u001b[43mquery\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    274\u001b[0m \u001b[38;5;66;03m# Check Number of requested results\u001b[39;00m\n",
+      "File \u001b[0;32m~/miniconda/envs/mlops/lib/python3.10/site-packages/chromadb/db/index/hnswlib.py:130\u001b[0m, in \u001b[0;36mHnswlib._check_dimensionality\u001b[0;34m(self, data)\u001b[0m\n\u001b[1;32m    129\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m dim \u001b[38;5;241m!=\u001b[39m idx_dim:\n\u001b[0;32m--> 130\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m InvalidDimensionException(\n\u001b[1;32m    131\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDimensionality of (\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mdim\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m) does not match index dimensionality (\u001b[39m\u001b[38;5;132;01m{\u001b[39;00midx_dim\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m)\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    132\u001b[0m     )\n",
+      "\u001b[0;31mInvalidDimensionException\u001b[0m: Dimensionality of (1536) does not match index dimensionality (384)",
+      "\nDuring handling of the above exception, another exception occurred:\n",
+      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[29], line 2\u001b[0m\n\u001b[1;32m      1\u001b[0m query \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mWhat is the zucchini?\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m----> 2\u001b[0m docs \u001b[38;5;241m=\u001b[39m \u001b[43mdocs_retriever\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msimilarity_search\u001b[49m\u001b[43m(\u001b[49m\u001b[43mquery\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m      4\u001b[0m \u001b[38;5;28mprint\u001b[39m(docs)\n",
+      "File \u001b[0;32m~/miniconda/envs/mlops/lib/python3.10/site-packages/langchain/vectorstores/chroma.py:182\u001b[0m, in \u001b[0;36mChroma.similarity_search\u001b[0;34m(self, query, k, filter, **kwargs)\u001b[0m\n\u001b[1;32m    165\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21msimilarity_search\u001b[39m(\n\u001b[1;32m    166\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    167\u001b[0m     query: \u001b[38;5;28mstr\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    170\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m    171\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m List[Document]:\n\u001b[1;32m    172\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"Run similarity search with Chroma.\u001b[39;00m\n\u001b[1;32m    173\u001b[0m \n\u001b[1;32m    174\u001b[0m \u001b[38;5;124;03m    Args:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    180\u001b[0m \u001b[38;5;124;03m        List[Document]: List of documents most similar to the query text.\u001b[39;00m\n\u001b[1;32m    181\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[0;32m--> 182\u001b[0m     docs_and_scores \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msimilarity_search_with_score\u001b[49m\u001b[43m(\u001b[49m\u001b[43mquery\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mk\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mfilter\u001b[39;49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mfilter\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m    183\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m [doc \u001b[38;5;28;01mfor\u001b[39;00m doc, _ \u001b[38;5;129;01min\u001b[39;00m docs_and_scores]\n",
+      "File \u001b[0;32m~/miniconda/envs/mlops/lib/python3.10/site-packages/langchain/vectorstores/chroma.py:229\u001b[0m, in \u001b[0;36mChroma.similarity_search_with_score\u001b[0;34m(self, query, k, filter, **kwargs)\u001b[0m\n\u001b[1;32m    227\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    228\u001b[0m     query_embedding \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_embedding_function\u001b[38;5;241m.\u001b[39membed_query(query)\n\u001b[0;32m--> 229\u001b[0m     results \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m__query_collection\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    230\u001b[0m \u001b[43m        \u001b[49m\u001b[43mquery_embeddings\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m[\u001b[49m\u001b[43mquery_embedding\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mn_results\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mk\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mwhere\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mfilter\u001b[39;49m\n\u001b[1;32m    231\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    233\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m _results_to_docs_and_scores(results)\n",
+      "File \u001b[0;32m~/miniconda/envs/mlops/lib/python3.10/site-packages/langchain/utils.py:52\u001b[0m, in \u001b[0;36mxor_args.<locals>.decorator.<locals>.wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m     46\u001b[0m     invalid_group_names \u001b[38;5;241m=\u001b[39m [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m, \u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(arg_groups[i]) \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m invalid_groups]\n\u001b[1;32m     47\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m     48\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mExactly one argument in each of the following\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     49\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m groups must be defined:\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     50\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m, \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(invalid_group_names)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     51\u001b[0m     )\n\u001b[0;32m---> 52\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/miniconda/envs/mlops/lib/python3.10/site-packages/langchain/vectorstores/chroma.py:128\u001b[0m, in \u001b[0;36mChroma.__query_collection\u001b[0;34m(self, query_texts, query_embeddings, n_results, where, **kwargs)\u001b[0m\n\u001b[1;32m    120\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    121\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_collection\u001b[38;5;241m.\u001b[39mquery(\n\u001b[1;32m    122\u001b[0m             query_texts\u001b[38;5;241m=\u001b[39mquery_texts,\n\u001b[1;32m    123\u001b[0m             query_embeddings\u001b[38;5;241m=\u001b[39mquery_embeddings,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    126\u001b[0m             \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[1;32m    127\u001b[0m         )\n\u001b[0;32m--> 128\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[43mchromadb\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mNotEnoughElementsException\u001b[49m:\n\u001b[1;32m    129\u001b[0m         logger\u001b[38;5;241m.\u001b[39merror(\n\u001b[1;32m    130\u001b[0m             \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mChroma collection \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_collection\u001b[38;5;241m.\u001b[39mname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    131\u001b[0m             \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcontains fewer than \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mi\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m elements.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    132\u001b[0m         )\n\u001b[1;32m    133\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m chromadb\u001b[38;5;241m.\u001b[39merrors\u001b[38;5;241m.\u001b[39mNotEnoughElementsException(\n\u001b[1;32m    134\u001b[0m     \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNo documents found for Chroma collection \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_collection\u001b[38;5;241m.\u001b[39mname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    135\u001b[0m )\n",
+      "\u001b[0;31mAttributeError\u001b[0m: module 'chromadb.errors' has no attribute 'NotEnoughElementsException'"
+     ]
+    }
+   ],
+   "source": [
+    "query = \"What is the zucchini?\"\n",
+    "docs = docs_retriever.similarity_search(query)\n",
+    "\n",
+    "print(docs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "96cd0d8a-d0c5-4828-81a3-5e908d3d7c9d",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "prompt = \"\"\"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.\n",
+    "\n",
+    "Context: {context}\n",
+    "\n",
+    "Question: {question}\n",
+    "Helpful Answer:\"\"\"\n",
+    "\n",
+    "prompt_template = PromptTemplate(\n",
+    "            template=prompt, input_variables=[\"context\", \"question\"]\n",
+    "        )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "e3ee9598-8ea6-45cc-8a27-6b3bb8f22c11",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "retriever_infos = [\n",
+    "    {\n",
+    "        \"name\": \"Food Guide\", \n",
+    "        \"description\": \"Good for answering questions about the menu\", \n",
+    "        \"retriever\": docs_retriever.as_retriever()\n",
+    "    },\n",
+    "    {\n",
+    "        \"name\": \"Bulevar Restaurant Details\", \n",
+    "        \"description\": \"Good for answering questions about Bulevar's hours, and restaurant details such as its mission, history, and owners.\", \n",
+    "        \"retriever\": bulevar_details_retriever.as_retriever()\n",
+    "    }\n",
+    "]\n",
+    "\n",
+    "chain = MultiRetrievalQAChain.from_retrievers(OpenAI(), retriever_infos, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "3d7393ea-3464-4ef3-bfe4-3ca93546791e",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new MultiRetrievalQAChain chain...\u001b[0m\n",
+      "Bulevar Restaurant Details: {'query': 'What is Bulevar?'}\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      " Bulevar is an excellent Mexican Cuisine restaurant with a laid back style to fine-dining created by Guy and Larry.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(chain.run(\"What is Bulevar?\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "774e945a-db65-4635-bb98-3d921fee912e",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new MultiRetrievalQAChain chain...\u001b[0m\n",
+      "Food Guide: {'query': \"What's special about Niman Ranch steaks?\"}\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      " Niman Ranch steaks are raised humanely and sustainably, and are dry aged for a minimum of 50 days, which concentrates the beef flavor.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(chain.run(\"What's special about Niman Ranch steaks?\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "4a934553-2904-4fdd-a632-96a9cad34a58",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new MultiRetrievalQAChain chain...\u001b[0m\n",
+      "Food Guide: {'query': 'Do you recommend dishes from Bulevar Restaurant?'}\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      " We cannot recommend dishes from Bulevar Restaurant, as we are not familiar with their menu.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(chain.run(\"Do you recommend it?\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "b1563ba0-d049-40b8-a917-f4b8c535be7e",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new MultiRetrievalQAChain chain...\u001b[0m\n",
+      "Food Guide: {'query': \"What's on the crab tostada?\"}\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      " The crab tostada is fried Masienda tortilla and seasoned with POW POW, topped with sliced avocado and a remoulade. It is then topped with jumbo lump crab meat lightly dressed and topped with radishes, freshly chopped chives, cilantro and Tajin powder, and a light drizzle of olive oil.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(chain.run(\"What's on the crab tostada?\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "d7c1e7c2-e534-4bbe-a6ce-53716c337864",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new MultiRetrievalQAChain chain...\u001b[0m\n",
+      "Bulevar Restaurant Details: {'query': 'When does the restaurant open?'}\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      " Bulevar is open Sunday through Wednesday from 5-9pm, and Thursday through Saturday from 4-10pm. It is open for lunch on Friday from 11-3pm.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(chain.run(\"When does the restaurant open?\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 99,
+   "id": "10a9a109-3c63-4824-bb5f-c5aafe92e7dd",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new MultiRetrievalQAChain chain...\u001b[0m\n",
+      "Food Guide: {'query': 'What allergies are in the Churros?'}\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      " Nuts(flour), Dairy, Cinnamon\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(chain.run(\"What allergies are in the Churros?\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 100,
+   "id": "5b7d843b-a95f-4794-ae90-b83073b30fae",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new MultiRetrievalQAChain chain...\u001b[0m\n",
+      "Food Guide: {'query': 'What are the Churros?'}\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      " The Churros are traditional mini churros deep fried and tossed with a cinnamon/sugar blend, served with house made dulce de leche and chocolate ganache dipping sauces, and topped with powdered sugar. They contain nuts (flour), dairy, and cinnamon.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(chain.run(\"What are the Churros?\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 101,
+   "id": "49ff4757-463f-4616-ad1e-0693a16e72bd",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new MultiRetrievalQAChain chain...\u001b[0m\n",
+      "Food Guide: {'query': 'What allergies are in the tarta de limon?'}\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      " Dairy, Egg, Honey, Citrus\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(chain.run(\"What allergies are on the tarta de limon?\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "59d54fdb-11da-437b-b513-a93d056ee713",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.10 (mlops)",
+   "language": "python",
+   "name": "mlops"
+  },
+  "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"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

app.py

@@ -0,0 +1,157 @@
+# gradio imports
+import gradio as gr
+import os
+import time
+
+# Imports
+import os
+
+import openai
+from langchain.chains import ConversationalRetrievalChain
+
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.document_loaders import TextLoader
+from langchain.text_splitter import MarkdownTextSplitter
+# from langchain.chat_models import ChatOpenAI
+# from langchain.text_splitter import CharacterTextSplitter
+from langchain.vectorstores import Chroma
+# from langchain.document_loaders import TextLoader
+
+# from langchain.memory import ConversationBufferMemory
+# from langchain.chat_models import ChatOpenAI
+from langchain.chains.router import MultiRetrievalQAChain
+from langchain.llms import OpenAI
+
+css="""
+#col-container {max-width: 700px; margin-left: auto; margin-right: auto;}
+"""
+
+title = """
+<div style="text-align: center;max-width: 700px;">
+    <h1>Chat about Bulevar's Menu</h1>
+</div>
+"""
+
+prompt_hints = """
+<div style="text-align: center;max-width: 700px;">
+    <p style="text-align: left;">What is in the crab tostada?<br />
+</div>
+"""
+
+# from index import PERSIST_DIRECTORY, CalendarIndex
+REST_PERSIST_DIRECTORY = "chromadb_bul_details"
+FOOD_GUIDE_PERSIST_DIRECTORY = "chromadb_food_guide"
+# Create embeddings
+
+# # create memory object
+# from langchain.memory import ConversationBufferMemory
+# memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+
+def loading_pdf():
+    return "Loading..."
+
+def loading_database(open_ai_key):
+    if open_ai_key is not None:
+        os.environ['OPENAI_API_KEY'] = open_ai_key
+        openai.api_key = open_ai_key
+        
+        embeddings = OpenAIEmbeddings(openai_api_key=open_ai_key)
+        # adds these restuarant details setnences
+        bulevar_restaurant_texts = [
+            "Bulevar is open Sunday through Wednesday from 5-9pm, and Thursday through Saturday from 4-10pm. It is open for lunch on Friday from 11-3pm",
+            "Bulevar is located in the Arboretum at 360 and Mopac, next to Eddie V's",
+            "Bulevar offers tasty Mexican Cuisine with a laid back style to fine-dining.",
+            "Bulevar is another restaurant created by Guy and Larry. With the success of their ATX Cocina, Bulevar has created another unique dining experience with high quality dishes."
+        ]
+        bulevar_details_retriever = Chroma.from_texts(bulevar_restaurant_texts, persist_directory=REST_PERSIST_DIRECTORY, embedding_function= embeddings)
+        if not os.path.exists(REST_PERSIST_DIRECTORY):
+            save_dir(bulevar_details_retriever)
+        loader = TextLoader('raw_text/food_guide.md')
+        documents = loader.load()
+
+        # adds the food_guide database
+        text_splitter = MarkdownTextSplitter(chunk_size=1000, chunk_overlap=0)
+        docs = text_splitter.split_documents(documents)
+
+        docs_retriever = Chroma.from_documents(docs, persist_directory=FOOD_GUIDE_PERSIST_DIRECTORY, embedding_function= embeddings)
+        
+        if not os.path.exists(FOOD_GUIDE_PERSIST_DIRECTORY):
+            save_dir(docs_retriever)
+        retriever_infos = [
+            {
+                "name": "Food Guide", 
+                "description": "Good for answering questions about the menu", 
+                "retriever": docs_retriever.as_retriever()
+            },
+            {
+                "name": "Bulevar Restaurant Details", 
+                "description": "Good for answering questions about Bulevar's hours, and restaurant details such as its mission, history, and owners.", 
+                "retriever": bulevar_details_retriever.as_retriever()
+            }
+        ]
+        global chain
+        chain = MultiRetrievalQAChain.from_retrievers(OpenAI(temperature=0, openai_api_key=open_ai_key), retriever_infos, verbose=True)
+        return "Ready"
+    else:
+        return "You forgot OpenAI API key"
+
+def save_dir(vectorstore_retriever):
+    vectorstore_retriever.persist()
+
+def add_text(history, text):
+    history = history + [(text, None)]
+    return history, ""
+
+
+def bot(history):
+    response = infer(history[-1][0], history)
+    history[-1][1] = ""
+    for character in response:     
+        history[-1][1] += character
+        time.sleep(0.05)
+        yield history
+    
+
+def infer(question, history):
+    # print("Here")
+    # print(question)
+    # print(history)
+    # print("DISPLAYED!!!")
+    res = []
+    # for human, ai in history[:-1]:
+    #     pair = (human, ai)
+    #     res.append(pair)
+    # print("now ask something new")
+    chat_history = res
+    query = question
+    result = chain({"input": query})
+    return result["result"]
+
+def update_message(question_component, chat_prompts):
+    question_component.value = chat_prompts.get_name()
+    return None
+
+with gr.Blocks(css=css) as demo:
+    with gr.Column(elem_id="col-container"):
+        gr.HTML(title)
+        with gr.Column():
+            with gr.Row():
+                openai_key = gr.Textbox(label="OpenAI API key", type="password")
+                submit_api_key = gr.Button("Submit")
+            with gr.Row():
+                langchain_status = gr.Textbox(label="Status", placeholder="", interactive=False)
+        
+        chatbot = gr.Chatbot([], elem_id="chatbot").style(height=350)
+        question = gr.Textbox(label="Question", placeholder="Type your question and hit Enter ")
+        submit_btn = gr.Button("Send Message")
+        gr.HTML(prompt_hints)
+        
+    submit_api_key.click(loading_database, inputs=[openai_key], outputs=[langchain_status], queue=False)
+    # demo.load(loading_database, None, langchain_status)
+    question.submit(add_text, [chatbot, question], [chatbot, question]).then(
+        bot, chatbot, chatbot
+    )
+    submit_btn.click(add_text, [chatbot, question], [chatbot, question]).then(
+        bot, chatbot, chatbot)
+
+demo.queue(concurrency_count=2, max_size=20).launch()

build_database.py

@@ -0,0 +1,103 @@
+import os
+import openai
+from dotenv import load_dotenv
+load_dotenv()
+
+print(os.getenv("OPENAI_API_KEY"))
+openai.api_key = os.getenv("OPENAI_API_KEY")
+
+from langchain import PromptTemplate
+from langchain.chains import RetrievalQA
+
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.chat_models import ChatOpenAI
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.text_splitter import MarkdownTextSplitter
+from langchain.vectorstores import Chroma
+from langchain.document_loaders import TextLoader
+
+from langchain.agents import Tool
+from langchain.memory import ConversationBufferMemory
+from langchain.chat_models import ChatOpenAI
+from langchain.utilities import SerpAPIWrapper
+from langchain.agents import initialize_agent
+from langchain.agents import AgentType
+# from langchain.vectorstores import FAISS
+
+from langchain.chains.router import MultiRetrievalQAChain
+from langchain.llms import OpenAI
+
+bulevar_restaurant_texts = [
+    "Bulevar is open Sunday through Wednesday from 5-9pm, and Thursday through Satruday from 4-10pm",
+    "Bulevar is located in the Arboretum at 360 and Mopac, next to Eddie V's",
+    "Bulevar offers tasty Mexican Cuisine, with a laid back style to fine-dining.",
+]
+bulevar_details_retriever = Chroma.from_texts(bulevar_restaurant_texts, embedding_function=  OpenAIEmbeddings())
+
+loader = TextLoader('raw_text/food_guide.md')
+documents = loader.load()
+
+text_splitter = MarkdownTextSplitter(chunk_size=750, chunk_overlap=35)
+docs = text_splitter.split_documents(documents)
+
+embeddings = OpenAIEmbeddings()
+
+docs_retriever = Chroma.from_documents(docs, embeddings)
+
+query = "Who is Jonny?"
+docs = docs_retriever.similarity_search(query)
+
+print(docs[0].page_content)
+
+prompt = """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.
+
+Context: {context}
+
+Question: {question}
+Helpful Answer:"""
+
+prompt_template = PromptTemplate(
+            template=prompt, input_variables=["context", "question"]
+        )
+qa_chain = RetrievalQA.from_chain_type(llm= ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0.0),  
+                                      chain_type='stuff', 
+                                      retriever=docs_retriever.as_retriever(), # the doc search
+                                    #   k=4, # takes the top 4 documents from the search
+                                        return_source_documents=True,
+                                        chain_type_kwargs={"prompt": prompt_template, "verbose": True},
+                                      )
+result = qa_chain({"query": query})
+print(result["result"])
+
+retriever_infos = [
+    {
+        "name": "Food Guide", 
+        "description": "Good for answering questions about Bulevar's dinner menu", 
+        "retriever": docs_retriever.as_retriever()
+    },
+    {
+        "name": "Bulevar Restaurant Details", 
+        "description": "Good for answering questions about Bulevar's hours, and restaurant details such as its mission, history, and owners.", 
+        "retriever": bulevar_details_retriever
+    }
+]
+
+chain = MultiRetrievalQAChain.from_retrievers(OpenAI(), retriever_infos, verbose=True)
+
+print(chain.run("What is Bulevar?"))
+print(chain.run("What kinds of meats are offered?"))
+
+
+# print(result["source_documents"])
+
+# question answer
+
+# How is Dialogues different from others?
+# Dialogues is different from others because it is a well-thought-out game with several players, built-in trust, a simple interface, and a feature that allows the user to select and align with the values that matter to them. It is designed to offer value to the individual and is not dictated by Silicon Valley. The founder has put everything they like about reading books, watching movies, and having conversations into building the app. The app also uses a measurement of normality based on duration of time to respond to abnormal and normal signals in the data.
+
+# How is the product coming along?
+# The product is nearly half a million lines of code and has an incredibly well-developed and defined product idea, but it is not yet ready for business as the creator is still seeking funding partners and wants to perfect more of it before opening up.
+
+# Who is Jonny?
+# Jonny is a person who has created a product related to AI, specifically LLMs and chatbot games, and is seeking investment from potential investors. He believes that his product can increase the valuation of existing companies and is confident in his engineering abilities. He also believes that the future of LLMs will be with writers and is focused on crafting writing to service each person at a personal level.
+

requirements.txt

@@ -0,0 +1,4 @@
+openai
+tiktoken
+chromadb
+langchain

steps.md

@@ -0,0 +1,14 @@
+# Steps
+
+1. Pre-process the knowledge base (docs)
+2. Store it in a database (embeddings)
+3. Inject content into GPT-3 prompt
+
+# App building specs
+
+1. langchain - for chaining prompts
+2. langflow - displays prompting with database
+3. gradio - integrates with huggingface (important, to easily demo the work being done, and let people pay for the openai results)
+4. pinecone (cloud vectorstore database, instead of chromadb which runs local)
+
+