forked from Archives/langchain
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
368 lines
18 KiB
Plaintext
368 lines
18 KiB
Plaintext
{
|
|
"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
|
|
}
|