Spaces:
Running
Running
File size: 18,848 Bytes
cfd3735 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# JSON Files\n",
"\n",
"The `JSONLoader` uses a specified [jq schema](https://en.wikipedia.org/wiki/Jq_(programming_language)) to parse the JSON files.\n",
"\n",
"This notebook shows how to use the `JSONLoader` to load [JSON](https://en.wikipedia.org/wiki/JSON) files into documents. A few examples of `jq` schema extracting different parts of a JSON file are also shown.\n",
"\n",
"Check this [manual](https://stedolan.github.io/jq/manual/#Basicfilters) for a detailed documentation of the `jq` syntax."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!pip install jq"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"jupyter": {
"outputs_hidden": true
}
},
"outputs": [],
"source": [
"from langchain.document_loaders import JSONLoader"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"from pathlib import Path\n",
"from pprint import pprint\n",
"\n",
"\n",
"file_path='./example_data/facebook_chat.json'\n",
"data = json.loads(Path(file_path).read_text())"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'image': {'creation_timestamp': 1675549016, 'uri': 'image_of_the_chat.jpg'},\n",
" 'is_still_participant': True,\n",
" 'joinable_mode': {'link': '', 'mode': 1},\n",
" 'magic_words': [],\n",
" 'messages': [{'content': 'Bye!',\n",
" 'sender_name': 'User 2',\n",
" 'timestamp_ms': 1675597571851},\n",
" {'content': 'Oh no worries! Bye',\n",
" 'sender_name': 'User 1',\n",
" 'timestamp_ms': 1675597435669},\n",
" {'content': 'No Im sorry it was my mistake, the blue one is not '\n",
" 'for sale',\n",
" 'sender_name': 'User 2',\n",
" 'timestamp_ms': 1675596277579},\n",
" {'content': 'I thought you were selling the blue one!',\n",
" 'sender_name': 'User 1',\n",
" 'timestamp_ms': 1675595140251},\n",
" {'content': 'Im not interested in this bag. Im interested in the '\n",
" 'blue one!',\n",
" 'sender_name': 'User 1',\n",
" 'timestamp_ms': 1675595109305},\n",
" {'content': 'Here is $129',\n",
" 'sender_name': 'User 2',\n",
" 'timestamp_ms': 1675595068468},\n",
" {'photos': [{'creation_timestamp': 1675595059,\n",
" 'uri': 'url_of_some_picture.jpg'}],\n",
" 'sender_name': 'User 2',\n",
" 'timestamp_ms': 1675595060730},\n",
" {'content': 'Online is at least $100',\n",
" 'sender_name': 'User 2',\n",
" 'timestamp_ms': 1675595045152},\n",
" {'content': 'How much do you want?',\n",
" 'sender_name': 'User 1',\n",
" 'timestamp_ms': 1675594799696},\n",
" {'content': 'Goodmorning! $50 is too low.',\n",
" 'sender_name': 'User 2',\n",
" 'timestamp_ms': 1675577876645},\n",
" {'content': 'Hi! Im interested in your bag. Im offering $50. Let '\n",
" 'me know if you are interested. Thanks!',\n",
" 'sender_name': 'User 1',\n",
" 'timestamp_ms': 1675549022673}],\n",
" 'participants': [{'name': 'User 1'}, {'name': 'User 2'}],\n",
" 'thread_path': 'inbox/User 1 and User 2 chat',\n",
" 'title': 'User 1 and User 2 chat'}\n"
]
}
],
"source": [
"pprint(data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Using `JSONLoader`\n",
"\n",
"Suppose we are interested in extracting the values under the `content` field within the `messages` key of the JSON data. This can easily be done through the `JSONLoader` as shown below."
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"loader = JSONLoader(\n",
" file_path='./example_data/facebook_chat.json',\n",
" jq_schema='.messages[].content')\n",
"\n",
"data = loader.load()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[Document(page_content='Bye!', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 1}),\n",
" Document(page_content='Oh no worries! Bye', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 2}),\n",
" Document(page_content='No Im sorry it was my mistake, the blue one is not for sale', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 3}),\n",
" Document(page_content='I thought you were selling the blue one!', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 4}),\n",
" Document(page_content='Im not interested in this bag. Im interested in the blue one!', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 5}),\n",
" Document(page_content='Here is $129', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 6}),\n",
" Document(page_content='', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 7}),\n",
" Document(page_content='Online is at least $100', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 8}),\n",
" Document(page_content='How much do you want?', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 9}),\n",
" Document(page_content='Goodmorning! $50 is too low.', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 10}),\n",
" Document(page_content='Hi! Im interested in your bag. Im offering $50. Let me know if you are interested. Thanks!', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 11})]\n"
]
}
],
"source": [
"pprint(data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Extracting metadata\n",
"\n",
"Generally, we want to include metadata available in the JSON file into the documents that we create from the content.\n",
"\n",
"The following demonstrates how metadata can be extracted using the `JSONLoader`.\n",
"\n",
"There are some key changes to be noted. In the previous example where we didn't collect the metadata, we managed to directly specify in the schema where the value for the `page_content` can be extracted from.\n",
"\n",
"```\n",
".messages[].content\n",
"```\n",
"\n",
"In the current example, we have to tell the loader to iterate over the records in the `messages` field. The jq_schema then has to be:\n",
"\n",
"```\n",
".messages[]\n",
"```\n",
"\n",
"This allows us to pass the records (dict) into the `metadata_func` that has to be implemented. The `metadata_func` is responsible for identifying which pieces of information in the record should be included in the metadata stored in the final `Document` object.\n",
"\n",
"Additionally, we now have to explicitly specify in the loader, via the `content_key` argument, the key from the record where the value for the `page_content` needs to be extracted from."
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"# Define the metadata extraction function.\n",
"def metadata_func(record: dict, metadata: dict) -> dict:\n",
"\n",
" metadata[\"sender_name\"] = record.get(\"sender_name\")\n",
" metadata[\"timestamp_ms\"] = record.get(\"timestamp_ms\")\n",
"\n",
" return metadata\n",
"\n",
"\n",
"loader = JSONLoader(\n",
" file_path='./example_data/facebook_chat.json',\n",
" jq_schema='.messages[]',\n",
" content_key=\"content\",\n",
" metadata_func=metadata_func\n",
")\n",
"\n",
"data = loader.load()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[Document(page_content='Bye!', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 1, 'sender_name': 'User 2', 'timestamp_ms': 1675597571851}),\n",
" Document(page_content='Oh no worries! Bye', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 2, 'sender_name': 'User 1', 'timestamp_ms': 1675597435669}),\n",
" Document(page_content='No Im sorry it was my mistake, the blue one is not for sale', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 3, 'sender_name': 'User 2', 'timestamp_ms': 1675596277579}),\n",
" Document(page_content='I thought you were selling the blue one!', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 4, 'sender_name': 'User 1', 'timestamp_ms': 1675595140251}),\n",
" Document(page_content='Im not interested in this bag. Im interested in the blue one!', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 5, 'sender_name': 'User 1', 'timestamp_ms': 1675595109305}),\n",
" Document(page_content='Here is $129', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 6, 'sender_name': 'User 2', 'timestamp_ms': 1675595068468}),\n",
" Document(page_content='', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 7, 'sender_name': 'User 2', 'timestamp_ms': 1675595060730}),\n",
" Document(page_content='Online is at least $100', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 8, 'sender_name': 'User 2', 'timestamp_ms': 1675595045152}),\n",
" Document(page_content='How much do you want?', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 9, 'sender_name': 'User 1', 'timestamp_ms': 1675594799696}),\n",
" Document(page_content='Goodmorning! $50 is too low.', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 10, 'sender_name': 'User 2', 'timestamp_ms': 1675577876645}),\n",
" Document(page_content='Hi! Im interested in your bag. Im offering $50. Let me know if you are interested. Thanks!', metadata={'source': '/Users/avsolatorio/WBG/langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 11, 'sender_name': 'User 1', 'timestamp_ms': 1675549022673})]\n"
]
}
],
"source": [
"pprint(data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now, you will see that the documents contain the metadata associated with the content we extracted."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## The `metadata_func`\n",
"\n",
"As shown above, the `metadata_func` accepts the default metadata generated by the `JSONLoader`. This allows full control to the user with respect to how the metadata is formatted.\n",
"\n",
"For example, the default metadata contains the `source` and the `seq_num` keys. However, it is possible that the JSON data contain these keys as well. The user can then exploit the `metadata_func` to rename the default keys and use the ones from the JSON data.\n",
"\n",
"The example below shows how we can modify the `source` to only contain information of the file source relative to the `langchain` directory."
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"# Define the metadata extraction function.\n",
"def metadata_func(record: dict, metadata: dict) -> dict:\n",
"\n",
" metadata[\"sender_name\"] = record.get(\"sender_name\")\n",
" metadata[\"timestamp_ms\"] = record.get(\"timestamp_ms\")\n",
" \n",
" if \"source\" in metadata:\n",
" source = metadata[\"source\"].split(\"/\")\n",
" source = source[source.index(\"langchain\"):]\n",
" metadata[\"source\"] = \"/\".join(source)\n",
"\n",
" return metadata\n",
"\n",
"\n",
"loader = JSONLoader(\n",
" file_path='./example_data/facebook_chat.json',\n",
" jq_schema='.messages[]',\n",
" content_key=\"content\",\n",
" metadata_func=metadata_func\n",
")\n",
"\n",
"data = loader.load()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[Document(page_content='Bye!', metadata={'source': 'langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 1, 'sender_name': 'User 2', 'timestamp_ms': 1675597571851}),\n",
" Document(page_content='Oh no worries! Bye', metadata={'source': 'langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 2, 'sender_name': 'User 1', 'timestamp_ms': 1675597435669}),\n",
" Document(page_content='No Im sorry it was my mistake, the blue one is not for sale', metadata={'source': 'langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 3, 'sender_name': 'User 2', 'timestamp_ms': 1675596277579}),\n",
" Document(page_content='I thought you were selling the blue one!', metadata={'source': 'langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 4, 'sender_name': 'User 1', 'timestamp_ms': 1675595140251}),\n",
" Document(page_content='Im not interested in this bag. Im interested in the blue one!', metadata={'source': 'langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 5, 'sender_name': 'User 1', 'timestamp_ms': 1675595109305}),\n",
" Document(page_content='Here is $129', metadata={'source': 'langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 6, 'sender_name': 'User 2', 'timestamp_ms': 1675595068468}),\n",
" Document(page_content='', metadata={'source': 'langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 7, 'sender_name': 'User 2', 'timestamp_ms': 1675595060730}),\n",
" Document(page_content='Online is at least $100', metadata={'source': 'langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 8, 'sender_name': 'User 2', 'timestamp_ms': 1675595045152}),\n",
" Document(page_content='How much do you want?', metadata={'source': 'langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 9, 'sender_name': 'User 1', 'timestamp_ms': 1675594799696}),\n",
" Document(page_content='Goodmorning! $50 is too low.', metadata={'source': 'langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 10, 'sender_name': 'User 2', 'timestamp_ms': 1675577876645}),\n",
" Document(page_content='Hi! Im interested in your bag. Im offering $50. Let me know if you are interested. Thanks!', metadata={'source': 'langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat.json', 'seq_num': 11, 'sender_name': 'User 1', 'timestamp_ms': 1675549022673})]\n"
]
}
],
"source": [
"pprint(data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Common JSON structures with jq schema\n",
"\n",
"The list below provides a reference to the possible `jq_schema` the user can use to extract content from the JSON data depending on the structure.\n",
"\n",
"```\n",
"JSON -> [{\"text\": ...}, {\"text\": ...}, {\"text\": ...}]\n",
"jq_schema -> \".[].text\"\n",
" \n",
"JSON -> {\"key\": [{\"text\": ...}, {\"text\": ...}, {\"text\": ...}]}\n",
"jq_schema -> \".key[].text\"\n",
"\n",
"JSON -> [\"...\", \"...\", \"...\"]\n",
"jq_schema -> \".[]\"\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.9.16"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
|