Upload 3 files

rag_json.ipynb

@@ -0,0 +1,345 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import SimpleDirectoryReader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "passbook_id = \"user001\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[Document(id_='2612cab8-acbb-48c8-87a7-839b628cf654', embedding=None, metadata={'file_path': 'passbooks\\\\user001.json', 'file_name': 'user001.json', 'file_type': 'application/json', 'file_size': 1878, 'creation_date': '2024-05-05', 'last_modified_date': '2024-05-06'}, excluded_embed_metadata_keys=['file_name', 'file_type', 'file_size', 'creation_date', 'last_modified_date', 'last_accessed_date'], excluded_llm_metadata_keys=['file_name', 'file_type', 'file_size', 'creation_date', 'last_modified_date', 'last_accessed_date'], relationships={}, text='[\\r\\n    {\\r\\n        \"entry_id\": 1,\\r\\n        \"date\": \"06-05-2024\",\\r\\n        \"description\": \"Groceries\",\\r\\n        \"debit\": 100.00,\\r\\n        \"credit\": null,\\r\\n        \"balance\": 25640.00\\r\\n    },\\r\\n\\r\\n    {\\r\\n        \"entry_id\": 2,\\r\\n        \"date\": \"06-05-2024\",\\r\\n        \"description\": \"Salary\",\\r\\n        \"debit\": null,\\r\\n        \"credit\": 1000.00,\\r\\n        \"balance\": 26640.00\\r\\n    },\\r\\n\\r\\n    {\\r\\n        \"entry_id\": 3,\\r\\n        \"date\": \"06-05-2024\",\\r\\n        \"description\": \"Rent\",\\r\\n        \"debit\": 500.00,\\r\\n        \"credit\": null,\\r\\n        \"balance\": 26140.00\\r\\n    },\\r\\n\\r\\n    {\\r\\n        \"entry_id\": 4,\\r\\n        \"date\": \"06-05-2024\",\\r\\n        \"description\": \"Electricity\",\\r\\n        \"debit\": 200.00,\\r\\n        \"credit\": null,\\r\\n        \"balance\": 25940.00\\r\\n    },\\r\\n\\r\\n    {\\r\\n        \"entry_id\": 5,\\r\\n        \"date\": \"06-05-2024\",\\r\\n        \"description\": \"Internet\",\\r\\n        \"debit\": 50.00,\\r\\n        \"credit\": null,\\r\\n        \"balance\": 25890.00\\r\\n    },\\r\\n\\r\\n    {\\r\\n        \"entry_id\": 6,\\r\\n        \"date\": \"06-05-2024\",\\r\\n        \"description\": \"Salary\",\\r\\n        \"debit\": null,\\r\\n        \"credit\": 1000.00,\\r\\n        \"balance\": 26890.00\\r\\n    },\\r\\n\\r\\n    {\\r\\n        \"entry_id\": 7,\\r\\n        \"date\": \"06-05-2024\",\\r\\n        \"description\": \"Groceries\",\\r\\n        \"debit\": 100.00,\\r\\n        \"credit\": null,\\r\\n        \"balance\": 26790.00\\r\\n    },\\r\\n\\r\\n    {\\r\\n        \"entry_id\": 8,\\r\\n        \"date\": \"06-05-2024\",\\r\\n        \"description\": \"Rent\",\\r\\n        \"debit\": 500.00,\\r\\n        \"credit\": null,\\r\\n        \"balance\": 26290.00\\r\\n    },\\r\\n\\r\\n    {\\r\\n        \"entry_id\": 9,\\r\\n        \"date\": \"06-05-2024\",\\r\\n        \"description\": \"Electricity\",\\r\\n        \"debit\": 200.00,\\r\\n        \"credit\": null,\\r\\n        \"balance\": 26090.00\\r\\n    },\\r\\n\\r\\n    {\\r\\n        \"entry_id\": 10,\\r\\n        \"date\": \"06-05-2024\",\\r\\n        \"description\": \"Internet\",\\r\\n        \"debit\": 50.00,\\r\\n        \"credit\": null,\\r\\n        \"balance\": 26040.00\\r\\n    }\\r\\n]', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\\n\\n{content}', metadata_template='{key}: {value}', metadata_seperator='\\n')]\n"
+     ]
+    }
+   ],
+   "source": [
+    "json_file = SimpleDirectoryReader(\n",
+    "    input_files = [f\"passbooks/{passbook_id}.json\"]\n",
+    "    ).load_data()\n",
+    "print(json_file)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core.prompts.prompts import SimpleInputPrompt\n",
+    "\n",
+    "system_prompt=\"\"\"\n",
+    "You are a Q&A assistant. Your goal is to answer questions as accurately as possible based on the instructions and context provided.\n",
+    "You will be provided with list of bank statements and you have to analyse the debits and credits based on the description and date and answer accordingly to user queries.\n",
+    "\"\"\"\n",
+    "\n",
+    "query_wrapper_prompt=SimpleInputPrompt(\"<|USER|>{query_str}<|ASSISTANT|>\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "3ac9bb85d9e1454cab179dd35d68acc9",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "login()\n",
+    "from huggingface_hub import login"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "67442839d6c2476ead1161d68bc1aeb8",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "model.safetensors.index.json:   0%|          | 0.00/26.8k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "d4247816f85c4b739086ee4f9d931524",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "e7d41810429e4265974a3fd1f1b08163",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "model-00001-of-00002.safetensors:   0%|          | 0.00/9.98G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "0d50b062af094dbe9b9e533f774afdad",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "model-00002-of-00002.safetensors:   0%|          | 0.00/3.50G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "84ff3eea97f940819f3faad537d6099d",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "e95f5b3a53c3415c86e47f4cdbec05ab",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "generation_config.json:   0%|          | 0.00/188 [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNING:root:Some parameters are on the meta device device because they were offloaded to the cpu and disk.\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "26503efe392d46dca3e2553747db4c13",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "tokenizer_config.json:   0%|          | 0.00/1.62k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "dd746f7ec6674bb2afad573344f8b95c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "tokenizer.model:   0%|          | 0.00/500k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "d4e2ffaa78024eadb753ea3d87b12489",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "tokenizer.json:   0%|          | 0.00/1.84M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "01c4aaaede0b40b28946a4bef395d0c6",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "special_tokens_map.json:   0%|          | 0.00/414 [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from llama_index.llms.huggingface import HuggingFaceLLM\n",
+    "import torch\n",
+    "\n",
+    "\n",
+    "llm = HuggingFaceLLM(\n",
+    "    context_window=4096,\n",
+    "    max_new_tokens=256,\n",
+    "    generate_kwargs={\"temperature\": 0.0, \"do_sample\": False},\n",
+    "    system_prompt=system_prompt,\n",
+    "    query_wrapper_prompt=query_wrapper_prompt,\n",
+    "    tokenizer_name=\"meta-llama/Llama-2-7b-chat-hf\",\n",
+    "    model_name=\"meta-llama/Llama-2-7b-chat-hf\",\n",
+    "    device_map=\"auto\",\n",
+    "    model_kwargs={\"torch_dtype\": torch.float16},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings.huggingface import HuggingFaceEmbeddings\n",
+    "from llama_index.legacy.embeddings.langchain import LangchainEmbedding\n",
+    "\n",
+    "embed_model=LangchainEmbedding(\n",
+    "    HuggingFaceEmbeddings(model_name=\"sentence-transformers/all-mpnet-base-v2\")\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\puran\\AppData\\Local\\Temp\\ipykernel_4904\\1600445012.py:2: DeprecationWarning: Call to deprecated class method from_defaults. (ServiceContext is deprecated, please use `llama_index.settings.Settings` instead.) -- Deprecated since version 0.10.0.\n",
+      "  service_context = ServiceContext.from_defaults(\n"
+     ]
+    }
+   ],
+   "source": [
+    "from llama_index.core import ServiceContext\n",
+    "service_context = ServiceContext.from_defaults(\n",
+    "    chunk_size=1024,\n",
+    "    llm=llm,\n",
+    "    embed_model=embed_model\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import VectorStoreIndex\n",
+    "\n",
+    "vector_index = VectorStoreIndex.from_documents(json_file, service_context=service_context)\n",
+    "query_engine = vector_index.as_query_engine()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\puran\\OneDrive\\Desktop\\RAG_Testing\\rag\\lib\\site-packages\\transformers\\generation\\configuration_utils.py:492: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `0.0` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.\n",
+      "  warnings.warn(\n",
+      "c:\\Users\\puran\\OneDrive\\Desktop\\RAG_Testing\\rag\\lib\\site-packages\\transformers\\generation\\configuration_utils.py:497: UserWarning: `do_sample` is set to `False`. However, `top_p` is set to `0.9` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `top_p`.\n",
+      "  warnings.warn(\n"
+     ]
+    }
+   ],
+   "source": [
+    "response=query_engine.query(\"where do i debit frequently?\")\n",
+    "print(response)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "rag",
+   "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": "3.9.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

user001.json

@@ -0,0 +1,91 @@
+[
+    {
+        "entry_id": 1,
+        "date": "06-05-2024",
+        "description": "Groceries",
+        "debit": 100.00,
+        "credit": null,
+        "balance": 25640.00
+    },
+
+    {
+        "entry_id": 2,
+        "date": "06-05-2024",
+        "description": "Salary",
+        "debit": null,
+        "credit": 1000.00,
+        "balance": 26640.00
+    },
+
+    {
+        "entry_id": 3,
+        "date": "06-05-2024",
+        "description": "Rent",
+        "debit": 500.00,
+        "credit": null,
+        "balance": 26140.00
+    },
+
+    {
+        "entry_id": 4,
+        "date": "06-05-2024",
+        "description": "Electricity",
+        "debit": 200.00,
+        "credit": null,
+        "balance": 25940.00
+    },
+
+    {
+        "entry_id": 5,
+        "date": "06-05-2024",
+        "description": "Internet",
+        "debit": 50.00,
+        "credit": null,
+        "balance": 25890.00
+    },
+
+    {
+        "entry_id": 6,
+        "date": "06-05-2024",
+        "description": "Salary",
+        "debit": null,
+        "credit": 1000.00,
+        "balance": 26890.00
+    },
+
+    {
+        "entry_id": 7,
+        "date": "06-05-2024",
+        "description": "Groceries",
+        "debit": 100.00,
+        "credit": null,
+        "balance": 26790.00
+    },
+
+    {
+        "entry_id": 8,
+        "date": "06-05-2024",
+        "description": "Rent",
+        "debit": 500.00,
+        "credit": null,
+        "balance": 26290.00
+    },
+
+    {
+        "entry_id": 9,
+        "date": "06-05-2024",
+        "description": "Electricity",
+        "debit": 200.00,
+        "credit": null,
+        "balance": 26090.00
+    },
+
+    {
+        "entry_id": 10,
+        "date": "06-05-2024",
+        "description": "Internet",
+        "debit": 50.00,
+        "credit": null,
+        "balance": 26040.00
+    }
+]

user002.json

@@ -0,0 +1,109 @@
+[
+    {
+        "entry_id": 1,
+        "date": "06-05-2024",
+        "description": "Movie Rental",
+        "debit": 300.00,
+        "credit": null,
+        "balance": 45000.00
+    },
+
+    {
+        "entry_id": 2,
+        "date": "06-05-2024",
+        "description": "Grocery",
+        "debit": 200.00,
+        "credit": null,
+        "balance": 44800.00
+    },
+
+    {
+        "entry_id": 3,
+        "date": "06-05-2024",
+        "description": "Salary",
+        "debit": null,
+        "credit": 50000.00,
+        "balance": 94800.00
+    },
+
+    {
+        "entry_id": 4,
+        "date": "06-05-2024",
+        "description": "Movie Rental",
+        "debit": 300.00,
+        "credit": null,
+        "balance": 94500.00
+    },
+
+    {
+        "entry_id": 5,
+        "date": "06-05-2024",
+        "description": "Grocery",
+        "debit": 200.00,
+        "credit": null,
+        "balance": 94300.00
+    },
+
+    {
+        "entry_id": 6,
+        "date": "06-05-2024",
+        "description": "Salary",
+        "debit": null,
+        "credit": 50000.00,
+        "balance": 144300.00
+    },
+
+    {
+        "entry_id": 7,
+        "date": "06-05-2024",
+        "description": "Movie Rental",
+        "debit": 300.00,
+        "credit": null,
+        "balance": 144000.00
+    },
+
+    {
+        "entry_id": 8,
+        "date": "06-05-2024",
+        "description": "Grocery",
+        "debit": 200.00,
+        "credit": null,
+        "balance": 143800.00
+    },
+
+    {
+        "entry_id": 9,
+        "date": "06-05-2024",
+        "description": "Salary",
+        "debit": null,
+        "credit": 50000.00,
+        "balance": 193800.00
+    },
+
+    {
+        "entry_id": 10,
+        "date": "06-05-2024",
+        "description": "Movie Rental",
+        "debit": 300.00,
+        "credit": null,
+        "balance": 193500.00
+    },
+
+    {
+        "entry_id": 11,
+        "date": "06-05-2024",
+        "description": "Grocery",
+        "debit": 200.00,
+        "credit": null,
+        "balance": 193300.00
+    },
+
+    {
+        "entry_id": 12,
+        "date": "06-05-2024",
+        "description": "Salary",
+        "debit": null,
+        "credit": 50000.00,
+        "balance": 243300.00
+    }
+]