From 3856dedff469b2ce08e3d416e9e351e2b8950e27 Mon Sep 17 00:00:00 2001 From: Leonid Ganeline Date: Thu, 4 Apr 2024 14:37:48 -0700 Subject: [PATCH] docs: `integrations/providers` update 9 (#19941) - Added missed providers - Added links, descriptions in related examples - Formatted in a consistent format Co-authored-by: Erick Friis --- .../document_loaders/acreom.ipynb | 2 +- .../document_loaders/athena.ipynb | 43 +++++++++++++-- .../document_loaders/bibtex.ipynb | 8 +-- .../document_loaders/couchbase.ipynb | 5 +- docs/docs/integrations/platforms/aws.mdx | 11 ++++ docs/docs/integrations/providers/acreom.mdx | 15 ++++++ docs/docs/integrations/providers/airbyte.mdx | 54 +++---------------- docs/docs/integrations/providers/alchemy.mdx | 20 +++++++ docs/docs/integrations/providers/arcgis.mdx | 27 ++++++++++ .../integrations/providers/assemblyai.mdx | 32 +++++++++++ docs/docs/integrations/providers/bibtex.mdx | 20 +++++++ .../integrations/providers/browserless.mdx | 18 +++++++ .../integrations/providers/byte_dance.mdx | 22 ++++++++ .../docs/integrations/providers/couchbase.mdx | 22 ++++++++ docs/docs/integrations/providers/cube.mdx | 21 ++++++++ .../integrations/providers/docusaurus.mdx | 20 +++++++ docs/docs/integrations/providers/dropbox.mdx | 21 ++++++++ .../docs/integrations/providers/etherscan.mdx | 18 +++++++ docs/docs/integrations/providers/fauna.mdx | 25 +++++++++ .../docs/integrations/providers/geopandas.mdx | 23 ++++++++ docs/docs/integrations/providers/github.mdx | 23 ++++++++ docs/docs/integrations/providers/huawei.mdx | 37 +++++++++++++ docs/docs/integrations/providers/iugu.mdx | 19 +++++++ docs/docs/integrations/providers/joplin.mdx | 19 +++++++ docs/docs/integrations/providers/lakefs.mdx | 18 +++++++ 25 files changed, 485 insertions(+), 58 deletions(-) create mode 100644 docs/docs/integrations/providers/acreom.mdx create mode 100644 docs/docs/integrations/providers/alchemy.mdx create mode 100644 docs/docs/integrations/providers/arcgis.mdx create mode 100644 docs/docs/integrations/providers/assemblyai.mdx create mode 100644 docs/docs/integrations/providers/bibtex.mdx create mode 100644 docs/docs/integrations/providers/browserless.mdx create mode 100644 docs/docs/integrations/providers/byte_dance.mdx create mode 100644 docs/docs/integrations/providers/couchbase.mdx create mode 100644 docs/docs/integrations/providers/cube.mdx create mode 100644 docs/docs/integrations/providers/docusaurus.mdx create mode 100644 docs/docs/integrations/providers/dropbox.mdx create mode 100644 docs/docs/integrations/providers/etherscan.mdx create mode 100644 docs/docs/integrations/providers/fauna.mdx create mode 100644 docs/docs/integrations/providers/geopandas.mdx create mode 100644 docs/docs/integrations/providers/github.mdx create mode 100644 docs/docs/integrations/providers/huawei.mdx create mode 100644 docs/docs/integrations/providers/iugu.mdx create mode 100644 docs/docs/integrations/providers/joplin.mdx create mode 100644 docs/docs/integrations/providers/lakefs.mdx diff --git a/docs/docs/integrations/document_loaders/acreom.ipynb b/docs/docs/integrations/document_loaders/acreom.ipynb index 0339337fbff..0be0506eed9 100644 --- a/docs/docs/integrations/document_loaders/acreom.ipynb +++ b/docs/docs/integrations/document_loaders/acreom.ipynb @@ -67,7 +67,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.10" + "version": "3.10.12" } }, "nbformat": 4, diff --git a/docs/docs/integrations/document_loaders/athena.ipynb b/docs/docs/integrations/document_loaders/athena.ipynb index 3fd655c0f0a..fada38b9841 100644 --- a/docs/docs/integrations/document_loaders/athena.ipynb +++ b/docs/docs/integrations/document_loaders/athena.ipynb @@ -8,7 +8,25 @@ "source": [ "# Athena\n", "\n", - "This notebooks goes over how to load documents from AWS Athena" + ">[Amazon Athena](https://aws.amazon.com/athena/) is a serverless, interactive analytics service built\n", + ">on open-source frameworks, supporting open-table and file formats. `Athena` provides a simplified,\n", + ">flexible way to analyze petabytes of data where it lives. Analyze data or build applications\n", + ">from an Amazon Simple Storage Service (S3) data lake and 30 data sources, including on-premises data\n", + ">sources or other cloud systems using SQL or Python. `Athena` is built on open-source `Trino`\n", + ">and `Presto` engines and `Apache Spark` frameworks, with no provisioning or configuration effort required.\n", + "\n", + "This notebook goes over how to load documents from `AWS Athena`." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Setting up\n", + "\n", + "Follow [instructions to set up an AWS accoung](https://docs.aws.amazon.com/athena/latest/ug/setting-up.html).\n", + "\n", + "Install a python library:" ] }, { @@ -22,6 +40,13 @@ "! pip install boto3" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Example" + ] + }, { "cell_type": "code", "execution_count": null, @@ -98,13 +123,23 @@ "provenance": [] }, "kernelspec": { - "display_name": "Python 3", + "display_name": "Python 3 (ipykernel)", + "language": "python", "name": "python3" }, "language_info": { - "name": "python" + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.12" } }, "nbformat": 4, - "nbformat_minor": 0 + "nbformat_minor": 4 } diff --git a/docs/docs/integrations/document_loaders/bibtex.ipynb b/docs/docs/integrations/document_loaders/bibtex.ipynb index 8a008b2e128..97cf32d8383 100644 --- a/docs/docs/integrations/document_loaders/bibtex.ipynb +++ b/docs/docs/integrations/document_loaders/bibtex.ipynb @@ -7,11 +7,11 @@ "source": [ "# BibTeX\n", "\n", - "> BibTeX is a file format and reference management system commonly used in conjunction with LaTeX typesetting. It serves as a way to organize and store bibliographic information for academic and research documents.\n", + ">[BibTeX](https://www.ctan.org/pkg/bibtex) is a file format and reference management system commonly used in conjunction with `LaTeX` typesetting. It serves as a way to organize and store bibliographic information for academic and research documents.\n", "\n", - "BibTeX files have a .bib extension and consist of plain text entries representing references to various publications, such as books, articles, conference papers, theses, and more. Each BibTeX entry follows a specific structure and contains fields for different bibliographic details like author names, publication title, journal or book title, year of publication, page numbers, and more.\n", + "`BibTeX` files have a `.bib` extension and consist of plain text entries representing references to various publications, such as books, articles, conference papers, theses, and more. Each `BibTeX` entry follows a specific structure and contains fields for different bibliographic details like author names, publication title, journal or book title, year of publication, page numbers, and more.\n", "\n", - "Bibtex files can also store the path to documents, such as `.pdf` files that can be retrieved." + "BibTeX files can also store the path to documents, such as `.pdf` files that can be retrieved." ] }, { @@ -184,7 +184,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.3" + "version": "3.10.12" } }, "nbformat": 4, diff --git a/docs/docs/integrations/document_loaders/couchbase.ipynb b/docs/docs/integrations/document_loaders/couchbase.ipynb index 5c41723b628..13a9def199d 100644 --- a/docs/docs/integrations/document_loaders/couchbase.ipynb +++ b/docs/docs/integrations/document_loaders/couchbase.ipynb @@ -6,7 +6,8 @@ "metadata": {}, "source": [ "# Couchbase\n", - "[Couchbase](http://couchbase.com/) is an award-winning distributed NoSQL cloud database that delivers unmatched versatility, performance, scalability, and financial value for all of your cloud, mobile, AI, and edge computing applications.\n" + "\n", + ">[Couchbase](http://couchbase.com/) is an award-winning distributed NoSQL cloud database that delivers unmatched versatility, performance, scalability, and financial value for all of your cloud, mobile, AI, and edge computing applications.\n" ] }, { @@ -195,7 +196,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.13" + "version": "3.10.12" } }, "nbformat": 4, diff --git a/docs/docs/integrations/platforms/aws.mdx b/docs/docs/integrations/platforms/aws.mdx index ffd8f08084d..fb97f763fb8 100644 --- a/docs/docs/integrations/platforms/aws.mdx +++ b/docs/docs/integrations/platforms/aws.mdx @@ -112,6 +112,17 @@ See a [usage example](/docs/integrations/document_loaders/amazon_textract). from langchain_community.document_loaders import AmazonTextractPDFLoader ``` +### Amazon Athena + +>[Amazon Athena](https://aws.amazon.com/athena/) is a serverless, interactive analytics service built +>on open-source frameworks, supporting open-table and file formats. + +See a [usage example](/docs/integrations/document_loaders/athena). + +```python +from langchain_community.document_loaders.athena import AthenaLoader +``` + ## Vector stores ### Amazon OpenSearch Service diff --git a/docs/docs/integrations/providers/acreom.mdx b/docs/docs/integrations/providers/acreom.mdx new file mode 100644 index 00000000000..78987870a2d --- /dev/null +++ b/docs/docs/integrations/providers/acreom.mdx @@ -0,0 +1,15 @@ +# Acreom + +[acreom](https://acreom.com) is a dev-first knowledge base with tasks running on local `markdown` files. + +## Installation and Setup + +No installation is required. + +## Document Loader + +See a [usage example](/docs/integrations/document_loaders/acreom). + +```python +from langchain_community.document_loaders import AcreomLoader +``` diff --git a/docs/docs/integrations/providers/airbyte.mdx b/docs/docs/integrations/providers/airbyte.mdx index 95b4c239f19..f1198b14861 100644 --- a/docs/docs/integrations/providers/airbyte.mdx +++ b/docs/docs/integrations/providers/airbyte.mdx @@ -3,11 +3,7 @@ >[Airbyte](https://github.com/airbytehq/airbyte) is a data integration platform for ELT pipelines from APIs, > databases & files to warehouses & lakes. It has the largest catalog of ELT connectors to data warehouses and databases. -## [AirbyteLoader](/docs/integrations/document_loaders/airbyte) - -This loader is built on top of [PyAirbyte](https://pypi.org/project/airbyte/) for easy setup and use. - -### Installation and Setup +## Installation and Setup ```bash pip install -U langchain-airbyte @@ -15,58 +11,22 @@ pip install -U langchain-airbyte :::note -Currently, the `airbyte` library does not support Pydantic v2. +Currently, the `langchain-airbyte` library does not support Pydantic v2. Please downgrade to Pydantic v1 to use this package. This package also currently requires Python 3.10+. ::: -The integration package doesn't have any global environment variables that need to be +The integration package doesn't require any global environment variables that need to be set, but some integrations (e.g. `source-github`) may need credentials passed in. -### Document Loader +## Document loader -`AirbyteLoader` class exposes a single document loader for Airbyte sources. +### AirbyteLoader + +See a [usage example](/docs/integrations/document_loaders/airbyte). ```python from langchain_airbyte import AirbyteLoader - -loader = AirbyteLoader( - source="source-faker", - stream="users", - config={"count": 100}, -) -docs = loader.load() -``` - -For more information, see the full [AirbyteLoader docs](/docs/integrations/document_loaders/airbyte). - -## AirbyteJSONLoader (Deprecated) - -This loader is deprecated and should be swapped out for `AirbyteLoader`, which doesn't require any of the docker setup! - -### Installation and Setup - -This instruction shows how to load any source from `Airbyte` into a local `JSON` file that can be read in as a document. - -**Prerequisites:** -Have `docker desktop` installed. - -**Steps:** -1. Clone Airbyte from GitHub - `git clone https://github.com/airbytehq/airbyte.git`. -2. Switch into Airbyte directory - `cd airbyte`. -3. Start Airbyte - `docker compose up`. -4. In your browser, just visit http://localhost:8000. You will be asked for a username and password. By default, that's username `airbyte` and password `password`. -5. Setup any source you wish. -6. Set destination as Local JSON, with specified destination path - lets say `/json_data`. Set up a manual sync. -7. Run the connection. -8. To see what files are created, navigate to: `file:///tmp/airbyte_local/`. - -### Document Loader - -See a [usage example](/docs/integrations/document_loaders/airbyte_json). - -```python -from langchain_community.document_loaders import AirbyteJSONLoader ``` diff --git a/docs/docs/integrations/providers/alchemy.mdx b/docs/docs/integrations/providers/alchemy.mdx new file mode 100644 index 00000000000..f1d7bbbcf75 --- /dev/null +++ b/docs/docs/integrations/providers/alchemy.mdx @@ -0,0 +1,20 @@ +# Alchemy + +>[Alchemy](https://www.alchemy.com) is the platform to build blockchain applications. + +## Installation and Setup + +Check out the [installation guide](/docs/integrations/document_loaders/blockchain). + +## Document loader + +### BlockchainLoader on the Alchemy platform + +See a [usage example](/docs/integrations/document_loaders/blockchain). + +```python +from langchain_community.document_loaders.blockchain import ( + BlockchainDocumentLoader, + BlockchainType, +) +``` diff --git a/docs/docs/integrations/providers/arcgis.mdx b/docs/docs/integrations/providers/arcgis.mdx new file mode 100644 index 00000000000..c7a00fd7ffc --- /dev/null +++ b/docs/docs/integrations/providers/arcgis.mdx @@ -0,0 +1,27 @@ +# ArcGIS + +>[ArcGIS](https://www.esri.com/en-us/arcgis/about-arcgis/overview) is a family of client, +> server and online geographic information system software developed and maintained by [Esri](https://www.esri.com/). +> +>`ArcGISLoader` uses the `arcgis` package. +> `arcgis` is a Python library for the vector and raster analysis, geocoding, map making, +> routing and directions. It administers, organizes and manages users, +> groups and information items in your GIS. +>It enables access to ready-to-use maps and curated geographic data from `Esri` +> and other authoritative sources, and works with your own data as well. + +## Installation and Setup + +We have to install the `arcgis` package. + +```bash +pip install -U arcgis +``` + +## Document Loader + +See a [usage example](/docs/integrations/document_loaders/arcgis). + +```python +from langchain_community.document_loaders import ArcGISLoader +``` diff --git a/docs/docs/integrations/providers/assemblyai.mdx b/docs/docs/integrations/providers/assemblyai.mdx new file mode 100644 index 00000000000..1a2ae8b2281 --- /dev/null +++ b/docs/docs/integrations/providers/assemblyai.mdx @@ -0,0 +1,32 @@ +# AssemblyAI + +>[AssemblyAI](https://www.assemblyai.com/) builds `Speech AI` models for tasks like +speech-to-text, speaker diarization, speech summarization, and more. +> `AssemblyAI’s` Speech AI models include accurate speech-to-text for voice data +> (such as calls, virtual meetings, and podcasts), speaker detection, sentiment analysis, +> chapter detection, PII redaction. + + + +## Installation and Setup + +Get your [API key](https://www.assemblyai.com/dashboard/signup). + +Install the `assemblyai` package. + +```bash +pip install -U assemblyai +``` + +## Document Loader + +### AssemblyAI Audio Transcript + +The `AssemblyAIAudioTranscriptLoader` transcribes audio files with the `AssemblyAI API` +and loads the transcribed text into documents. + +See a [usage example](/docs/integrations/document_loaders/assemblyai). + +```python +from langchain_community.document_loaders import AssemblyAIAudioTranscriptLoader +``` diff --git a/docs/docs/integrations/providers/bibtex.mdx b/docs/docs/integrations/providers/bibtex.mdx new file mode 100644 index 00000000000..09cc2fd93d1 --- /dev/null +++ b/docs/docs/integrations/providers/bibtex.mdx @@ -0,0 +1,20 @@ +# BibTeX + +>[BibTeX](https://www.ctan.org/pkg/bibtex) is a file format and reference management system commonly used in conjunction with `LaTeX` typesetting. It serves as a way to organize and store bibliographic information for academic and research documents. + +## Installation and Setup + +We have to install the `bibtexparser` and `pymupdf` packages. + +```bash +pip install bibtexparser pymupdf +``` + + +## Document loader + +See a [usage example](/docs/integrations/document_loaders/bibtex). + +```python +from langchain_community.document_loaders import BibtexLoader +``` diff --git a/docs/docs/integrations/providers/browserless.mdx b/docs/docs/integrations/providers/browserless.mdx new file mode 100644 index 00000000000..0fe4463af92 --- /dev/null +++ b/docs/docs/integrations/providers/browserless.mdx @@ -0,0 +1,18 @@ +# Browserless + +>[Browserless](https://www.browserless.io/docs/start) is a service that allows you to +> run headless Chrome instances in the cloud. It’s a great way to run browser-based +> automation at scale without having to worry about managing your own infrastructure. + +## Installation and Setup + +We have to get the API key [here](https://www.browserless.io/pricing/). + + +## Document loader + +See a [usage example](/docs/integrations/document_loaders/browserless). + +```python +from langchain_community.document_loaders import BrowserlessLoader +``` diff --git a/docs/docs/integrations/providers/byte_dance.mdx b/docs/docs/integrations/providers/byte_dance.mdx new file mode 100644 index 00000000000..8746bcf519f --- /dev/null +++ b/docs/docs/integrations/providers/byte_dance.mdx @@ -0,0 +1,22 @@ +# ByteDance + +>[ByteDance](https://bytedance.com/) is a Chinese internet technology company. + +## Installation and Setup + +Get the access token. +You can find the access instructions [here](https://open.larksuite.com/document) + + +## Document Loader + +### Lark Suite + +>[Lark Suite](https://www.larksuite.com/) is an enterprise collaboration platform +> developed by `ByteDance`. + +See a [usage example](/docs/integrations/document_loaders/larksuite). + +```python +from langchain_community.document_loaders.larksuite import LarkSuiteDocLoader +``` diff --git a/docs/docs/integrations/providers/couchbase.mdx b/docs/docs/integrations/providers/couchbase.mdx new file mode 100644 index 00000000000..9eff6cc0b6f --- /dev/null +++ b/docs/docs/integrations/providers/couchbase.mdx @@ -0,0 +1,22 @@ +# Couchbase + +>[Couchbase](http://couchbase.com/) is an award-winning distributed NoSQL cloud database +> that delivers unmatched versatility, performance, scalability, and financial value +> for all of your cloud, mobile, AI, and edge computing applications. + +## Installation and Setup + +We have to install the `couchbase`package. + +```bash +pip install couchbase +``` + + +## Document loader + +See a [usage example](/docs/integrations/document_loaders/couchbase). + +```python +from langchain_community.document_loaders.couchbase import CouchbaseLoader +``` diff --git a/docs/docs/integrations/providers/cube.mdx b/docs/docs/integrations/providers/cube.mdx new file mode 100644 index 00000000000..9393bc36aa2 --- /dev/null +++ b/docs/docs/integrations/providers/cube.mdx @@ -0,0 +1,21 @@ +# Cube + +>[Cube](https://cube.dev/) is the Semantic Layer for building data apps. It helps +> data engineers and application developers access data from modern data stores, +> organize it into consistent definitions, and deliver it to every application. + +## Installation and Setup + +We have to get the API key and the URL of the Cube instance. See +[these instructions](https://cube.dev/docs/product/apis-integrations/rest-api#configuration-base-path). + + +## Document loader + +### Cube Semantic Layer + +See a [usage example](/docs/integrations/document_loaders/cube_semantic). + +```python +from langchain_community.document_loaders import CubeSemanticLoader +``` diff --git a/docs/docs/integrations/providers/docusaurus.mdx b/docs/docs/integrations/providers/docusaurus.mdx new file mode 100644 index 00000000000..e137d627724 --- /dev/null +++ b/docs/docs/integrations/providers/docusaurus.mdx @@ -0,0 +1,20 @@ +# Docusaurus + +>[Docusaurus](https://docusaurus.io/) is a static-site generator which provides +> out-of-the-box documentation features. + + +## Installation and Setup + + +```bash +pip install -U beautifulsoup4 lxml +``` + +## Document Loader + +See a [usage example](/docs/integrations/document_loaders/docusaurus). + +```python +from langchain_community.document_loaders import DocusaurusLoader +``` diff --git a/docs/docs/integrations/providers/dropbox.mdx b/docs/docs/integrations/providers/dropbox.mdx new file mode 100644 index 00000000000..590a58b9a68 --- /dev/null +++ b/docs/docs/integrations/providers/dropbox.mdx @@ -0,0 +1,21 @@ +# Dropbox + +>[Dropbox](https://en.wikipedia.org/wiki/Dropbox) is a file hosting service that brings everything-traditional +> files, cloud content, and web shortcuts together in one place. + + +## Installation and Setup + +See the detailed [installation guide](/docs/integrations/document_loaders/dropbox#prerequisites). + +```bash +pip install -U dropbox +``` + +## Document Loader + +See a [usage example](/docs/integrations/document_loaders/dropbox). + +```python +from langchain_community.document_loaders import DropboxLoader +``` diff --git a/docs/docs/integrations/providers/etherscan.mdx b/docs/docs/integrations/providers/etherscan.mdx new file mode 100644 index 00000000000..cc4e197b289 --- /dev/null +++ b/docs/docs/integrations/providers/etherscan.mdx @@ -0,0 +1,18 @@ +# Etherscan + +>[Etherscan](https://docs.etherscan.io/) is the leading blockchain explorer, +> search, API and analytics platform for `Ethereum`, a decentralized smart contracts platform. + + +## Installation and Setup + +See the detailed [installation guide](/docs/integrations/document_loaders/etherscan). + + +## Document Loader + +See a [usage example](/docs/integrations/document_loaders/etherscan). + +```python +from langchain_community.document_loaders import EtherscanLoader +``` diff --git a/docs/docs/integrations/providers/fauna.mdx b/docs/docs/integrations/providers/fauna.mdx new file mode 100644 index 00000000000..252c0101d2e --- /dev/null +++ b/docs/docs/integrations/providers/fauna.mdx @@ -0,0 +1,25 @@ +# Fauna + +>[Fauna](https://fauna.com/) is a distributed document-relational database +> that combines the flexibility of documents with the power of a relational, +> ACID compliant database that scales across regions, clouds or the globe. + + +## Installation and Setup + +We have to get the secret key. +See the detailed [guide](https://docs.fauna.com/fauna/current/learn/security_model/). + +We have to install the `fauna` package. + +```bash +pip install -U fauna +``` + +## Document Loader + +See a [usage example](/docs/integrations/document_loaders/fauna). + +```python +from langchain_community.document_loaders.fauna import FaunaLoader +``` diff --git a/docs/docs/integrations/providers/geopandas.mdx b/docs/docs/integrations/providers/geopandas.mdx new file mode 100644 index 00000000000..c14a29c40bd --- /dev/null +++ b/docs/docs/integrations/providers/geopandas.mdx @@ -0,0 +1,23 @@ +# Geopandas + +>[GeoPandas](https://geopandas.org/) is an open source project to make working +> with geospatial data in python easier. `GeoPandas` extends the datatypes used by +> `pandas` to allow spatial operations on geometric types. +> Geometric operations are performed by `shapely`. + + +## Installation and Setup + +We have to install several python packages. + +```bash +pip install -U sodapy pandas geopandas +``` + +## Document Loader + +See a [usage example](/docs/integrations/document_loaders/geopandas). + +```python +from langchain_community.document_loaders import OpenCityDataLoader +``` diff --git a/docs/docs/integrations/providers/github.mdx b/docs/docs/integrations/providers/github.mdx new file mode 100644 index 00000000000..2030e985948 --- /dev/null +++ b/docs/docs/integrations/providers/github.mdx @@ -0,0 +1,23 @@ +# GitHub + +>[GitHub](https://github.com/) is a developer platform that allows developers to create, +> store, manage and share their code. It uses `Git` software, providing the +> distributed version control of Git plus access control, bug tracking, +> software feature requests, task management, continuous integration, and wikis for every project. + + +## Installation and Setup + +To access the GitHub API, you need a [personal access token](https://github.com/settings/tokens). + + +## Document Loader + +There are two document loaders available for GitHub. + +See a [usage example](/docs/integrations/document_loaders/github). + +```python +from langchain_community.document_loaders import GitHubIssuesLoader +from langchain.document_loaders import GithubFileLoader +``` diff --git a/docs/docs/integrations/providers/huawei.mdx b/docs/docs/integrations/providers/huawei.mdx new file mode 100644 index 00000000000..22b12ca717f --- /dev/null +++ b/docs/docs/integrations/providers/huawei.mdx @@ -0,0 +1,37 @@ +# Huawei + +>[Huawei Technologies Co., Ltd.](https://www.huawei.com/) is a Chinese multinational +> digital communications technology corporation. +> +>[Huawei Cloud](https://www.huaweicloud.com/intl/en-us/product/) provides a comprehensive suite of +> global cloud computing services. + + +## Installation and Setup + +To access the `Huawei Cloud`, you need an access token. + +You also have to install a python library: + +```bash +pip install -U esdk-obs-python +``` + + +## Document Loader + +### Huawei OBS Directory + +See a [usage example](/docs/integrations/document_loaders/huawei_obs_directory). + +```python +from langchain_community.document_loaders import OBSDirectoryLoader +``` + +### Huawei OBS File + +See a [usage example](/docs/integrations/document_loaders/huawei_obs_file). + +```python +from langchain_community.document_loaders.obs_file import OBSFileLoader +``` diff --git a/docs/docs/integrations/providers/iugu.mdx b/docs/docs/integrations/providers/iugu.mdx new file mode 100644 index 00000000000..5abbeaa8a06 --- /dev/null +++ b/docs/docs/integrations/providers/iugu.mdx @@ -0,0 +1,19 @@ +# Iugu + +>[Iugu](https://www.iugu.com/) is a Brazilian services and software as a service (SaaS) +> company. It offers payment-processing software and application programming +> interfaces for e-commerce websites and mobile applications. + + +## Installation and Setup + +The `Iugu API` requires an access token, which can be found inside of the `Iugu` dashboard. + + +## Document Loader + +See a [usage example](/docs/integrations/document_loaders/iugu). + +```python +from langchain_community.document_loaders import IuguLoader +``` diff --git a/docs/docs/integrations/providers/joplin.mdx b/docs/docs/integrations/providers/joplin.mdx new file mode 100644 index 00000000000..b3c83acc5ff --- /dev/null +++ b/docs/docs/integrations/providers/joplin.mdx @@ -0,0 +1,19 @@ +# Joplin + +>[Joplin](https://joplinapp.org/) is an open-source note-taking app. It captures your thoughts +> and securely accesses them from any device. + + +## Installation and Setup + +The `Joplin API` requires an access token. +You can find installation instructions [here](https://joplinapp.org/api/references/rest_api/). + + +## Document Loader + +See a [usage example](/docs/integrations/document_loaders/joplin). + +```python +from langchain_community.document_loaders import JoplinLoader +``` diff --git a/docs/docs/integrations/providers/lakefs.mdx b/docs/docs/integrations/providers/lakefs.mdx new file mode 100644 index 00000000000..c38d5bb4928 --- /dev/null +++ b/docs/docs/integrations/providers/lakefs.mdx @@ -0,0 +1,18 @@ +# lakeFS + +>[lakeFS](https://docs.lakefs.io/) provides scalable version control over +> the data lake, and uses Git-like semantics to create and access those versions. + +## Installation and Setup + +Get the `ENDPOINT`, `LAKEFS_ACCESS_KEY`, and `LAKEFS_SECRET_KEY`. +You can find installation instructions [here](https://docs.lakefs.io/quickstart/launch.html). + + +## Document Loader + +See a [usage example](/docs/integrations/document_loaders/lakefs). + +```python +from langchain_community.document_loaders import LakeFSLoader +```