Vwp/docs improved document loaders (#4006)

Huge thanks to @leo-gan for improving the document loaders notebooks

---------

Co-authored-by: Leonid Ganeline <leo.gan.57@gmail.com>
This commit is contained in:
Zander Chase
2023-05-02 15:24:53 -07:00
committed by GitHub
parent 1c68cbdb28
commit aa38355999
57 changed files with 1227 additions and 779 deletions

View File

@@ -6,13 +6,24 @@
"source": [
"### Facebook Chat\n",
"\n",
"This notebook covers how to load data from the Facebook Chats into a format that can be ingested into LangChain."
"This notebook covers how to load data from the [Facebook Chats](https://www.facebook.com/business/help/1646890868956360) into a format that can be ingested into LangChain."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#pip install pandas"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.document_loaders import FacebookChatLoader"
@@ -21,7 +32,9 @@
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"loader = FacebookChatLoader(\"example_data/facebook_chat.json\")"
@@ -29,16 +42,18 @@
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"execution_count": 7,
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"[Document(page_content='User 2 on 2023-02-05 12:46:11: Bye!\\n\\nUser 1 on 2023-02-05 12:43:55: Oh no worries! Bye\\n\\nUser 2 on 2023-02-05 12:24:37: No Im sorry it was my mistake, the blue one is not for sale\\n\\nUser 1 on 2023-02-05 12:05:40: I thought you were selling the blue one!\\n\\nUser 1 on 2023-02-05 12:05:09: Im not interested in this bag. Im interested in the blue one!\\n\\nUser 2 on 2023-02-05 12:04:28: Here is $129\\n\\nUser 2 on 2023-02-05 12:04:05: Online is at least $100\\n\\nUser 1 on 2023-02-05 11:59:59: How much do you want?\\n\\nUser 2 on 2023-02-05 07:17:56: Goodmorning! $50 is too low.\\n\\nUser 1 on 2023-02-04 23:17:02: Hi! Im interested in your bag. Im offering $50. Let me know if you are interested. Thanks!\\n\\n', lookup_str='', metadata={'source': 'docs/modules/document_loaders/examples/example_data/facebook_chat.json'}, lookup_index=0)]"
"[Document(page_content='User 2 on 2023-02-05 03:46:11: Bye!\\n\\nUser 1 on 2023-02-05 03:43:55: Oh no worries! Bye\\n\\nUser 2 on 2023-02-05 03:24:37: No Im sorry it was my mistake, the blue one is not for sale\\n\\nUser 1 on 2023-02-05 03:05:40: I thought you were selling the blue one!\\n\\nUser 1 on 2023-02-05 03:05:09: Im not interested in this bag. Im interested in the blue one!\\n\\nUser 2 on 2023-02-05 03:04:28: Here is $129\\n\\nUser 2 on 2023-02-05 03:04:05: Online is at least $100\\n\\nUser 1 on 2023-02-05 02:59:59: How much do you want?\\n\\nUser 2 on 2023-02-04 22:17:56: Goodmorning! $50 is too low.\\n\\nUser 1 on 2023-02-04 14:17:02: Hi! Im interested in your bag. Im offering $50. Let me know if you are interested. Thanks!\\n\\n', metadata={'source': 'example_data/facebook_chat.json'})]"
]
},
"execution_count": 3,
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
@@ -64,7 +79,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.1"
"version": "3.10.6"
},
"vscode": {
"interpreter": {
@@ -73,5 +88,5 @@
}
},
"nbformat": 4,
"nbformat_minor": 2
"nbformat_minor": 4
}