# Rezolve AI Ingestion
Rezolve AI Ingestion is a proprietary package developed by Rezolve.ai for ingesting and processing SharePoint data with AI capabilities. This package is designed for internal use within Rezolve.ai and is not intended for public distribution.
## Features
- Connect to SharePoint and retrieve data
- Process and analyze SharePoint content using AI
- Integrate with Pinecone for efficient data storage and retrieval
- Utilize OpenAI's language models for advanced text processing
## Installation
This package is not available on public package repositories. To install, clone the repository from our private Git server:
```
git clone https://your-private-repo-url.com/rezolve-ai-ingestion.git
cd rezolve-ai-ingestion
pip install -e .
```
## Usage
Here's a basic example of how to use the Rezolve AI Ingestion package:
```python
from SharepointConnect.Models.Ingest import IngestSharepoint
from SharepointConnect.Processor import SharePointProcessor
# Set up your configuration
request_data = IngestSharepoint()
request_data.authorization.azure_tid = "YOUR_TENANT_ID"
request_data.authorization.client_id = "YOUR_CLIENT_ID"
request_data.authorization.thumbprint = "YOUR_THUMBPRINT"
request_data.authorization.key = "YOUR_PRIVATE_KEY"
request_data.rezolve.index = "YOUR_PINECONE_INDEX"
request_data.rezolve.namespace = "YOUR_REZOLVE_NAMESPACE"
request_data.rezolve.environment = "YOUR_PINECONE_ENVIRONMENT"
request_data.rezolve.db_key = "YOUR_PINECONE_API_KEY"
request_data.rezolve.llm_key = "YOUR_OPENAI_API_KEY"
request_data.rezolve.embedding_model = "YOUR_EMBED_MODEL"
request_data.drives.sites = ["YOUR_SITE_URLS"]
request_data.pages.pages = ["YOUR_SITE_PAGES"]
# Process SharePoint data
processor = SharePointProcessor(request_data)
processor.process_sharepoint()
processed_files = processor.processed_files
# You can now work with the processed_files data
```
## Configuration
Ensure you have the following environment variables set or provide them in your configuration:
- TENANT_ID
- CLIENT_ID
- THUMBPRINT
- PRIVATE_KEY
- PINECONE_INDEX
- REZOLVE_NAMESPACE
- PINECONE_ENVIRONMENT
- PINECONE_API_KEY
- OPENAI_API_KEY
- EMBED_MODEL
### Windows
Save the following script as `setup_windows.ps1`:
```powershell
# Check if running as administrator
if (-NOT ([Security.Principal.WindowsPrincipal][Security.Principal.WindowsIdentity]::GetCurrent()).IsInRole([Security.Principal.WindowsBuiltInRole] "Administrator")) {
Write-Warning "You do not have Administrator rights to run this script!`nPlease re-run this script as an Administrator!"
Break
}
# Install Chocolatey
Set-ExecutionPolicy Bypass -Scope Process -Force;
[System.Net.ServicePointManager]::SecurityProtocol = [System.Net.ServicePointManager]::SecurityProtocol -bor 3072;
iex ((New-Object System.Net.WebClient).DownloadString('https://chocolatey.org/install.ps1'))
# Install dependencies using Chocolatey
choco install -y python3 wget gnupg2 xvfb unzip ffmpeg lame sox
# Install Tesseract OCR
choco install -y tesseract
$env:Path += ";C:\Program Files\Tesseract-OCR"
[Environment]::SetEnvironmentVariable("Path", $env:Path, [EnvironmentVariableTarget]::Machine)
# Download and install additional language data for Tesseract
$tessDataUrl = "https://github.com/tesseract-ocr/tessdata/raw/main/"
$tessDataDir = "C:\Program Files\Tesseract-OCR\tessdata"
$languages = @("eng", "deu", "fra", "spa") # Add or remove languages as needed
foreach ($lang in $languages) {
$url = $tessDataUrl + $lang + ".traineddata"
$output = $tessDataDir + "\" + $lang + ".traineddata"
Invoke-WebRequest -Uri $url -OutFile $output
}
# Refresh environment variables
$env:Path = [System.Environment]::GetEnvironmentVariable("Path","Machine") + ";" + [System.Environment]::GetEnvironmentVariable("Path","User")
# Upgrade pip
python -m pip install --upgrade pip
# Install the Rezolve AI Ingestion package
pip install git+https://your-private-repo-url.com/rezolve-ai-ingestion.git
Write-Host "Installation complete. Please restart your PowerShell."
## Support
For support, please contact the internal development team at Rezolve.ai.
## License
This project is proprietary and confidential. Unauthorized copying, transferring or reproduction of the contents of this project, via any medium is strictly prohibited.
Copyright (c) 2024 Rezolve.ai. All Rights Reserved.
Raw data
{
"_id": null,
"home_page": null,
"name": "rezolve-ai-ingestion",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": null,
"keywords": "sharepoint, ai, ingestion, data processing, rezolve",
"author": null,
"author_email": "Joshua O'Brien <josh@rezolve.ai>, Kushagra Kesarwani <kushagra.kessarwani@rezolve.ai>",
"download_url": "https://files.pythonhosted.org/packages/9e/2e/2db51cb373cb6ebc2d6f7df12c037ad9f99e5fcf2195a332d7c639c7c75b/rezolve_ai_ingestion-0.1.4.tar.gz",
"platform": null,
"description": "# Rezolve AI Ingestion\n\nRezolve AI Ingestion is a proprietary package developed by Rezolve.ai for ingesting and processing SharePoint data with AI capabilities. This package is designed for internal use within Rezolve.ai and is not intended for public distribution.\n\n## Features\n\n- Connect to SharePoint and retrieve data\n- Process and analyze SharePoint content using AI\n- Integrate with Pinecone for efficient data storage and retrieval\n- Utilize OpenAI's language models for advanced text processing\n\n## Installation\n\nThis package is not available on public package repositories. To install, clone the repository from our private Git server:\n\n```\ngit clone https://your-private-repo-url.com/rezolve-ai-ingestion.git\ncd rezolve-ai-ingestion\npip install -e .\n```\n\n## Usage\n\nHere's a basic example of how to use the Rezolve AI Ingestion package:\n\n```python\nfrom SharepointConnect.Models.Ingest import IngestSharepoint\nfrom SharepointConnect.Processor import SharePointProcessor\n\n# Set up your configuration\nrequest_data = IngestSharepoint()\nrequest_data.authorization.azure_tid = \"YOUR_TENANT_ID\"\nrequest_data.authorization.client_id = \"YOUR_CLIENT_ID\"\nrequest_data.authorization.thumbprint = \"YOUR_THUMBPRINT\"\nrequest_data.authorization.key = \"YOUR_PRIVATE_KEY\"\n\nrequest_data.rezolve.index = \"YOUR_PINECONE_INDEX\"\nrequest_data.rezolve.namespace = \"YOUR_REZOLVE_NAMESPACE\"\nrequest_data.rezolve.environment = \"YOUR_PINECONE_ENVIRONMENT\"\nrequest_data.rezolve.db_key = \"YOUR_PINECONE_API_KEY\"\n\nrequest_data.rezolve.llm_key = \"YOUR_OPENAI_API_KEY\"\nrequest_data.rezolve.embedding_model = \"YOUR_EMBED_MODEL\"\n\nrequest_data.drives.sites = [\"YOUR_SITE_URLS\"]\nrequest_data.pages.pages = [\"YOUR_SITE_PAGES\"]\n\n# Process SharePoint data\nprocessor = SharePointProcessor(request_data)\nprocessor.process_sharepoint()\nprocessed_files = processor.processed_files\n\n# You can now work with the processed_files data\n```\n\n## Configuration\n\nEnsure you have the following environment variables set or provide them in your configuration:\n\n- TENANT_ID\n- CLIENT_ID\n- THUMBPRINT\n- PRIVATE_KEY\n- PINECONE_INDEX\n- REZOLVE_NAMESPACE\n- PINECONE_ENVIRONMENT\n- PINECONE_API_KEY\n- OPENAI_API_KEY\n- EMBED_MODEL\n\n### Windows\n\nSave the following script as `setup_windows.ps1`:\n\n```powershell\n# Check if running as administrator\nif (-NOT ([Security.Principal.WindowsPrincipal][Security.Principal.WindowsIdentity]::GetCurrent()).IsInRole([Security.Principal.WindowsBuiltInRole] \"Administrator\")) {\n Write-Warning \"You do not have Administrator rights to run this script!`nPlease re-run this script as an Administrator!\"\n Break\n}\n\n# Install Chocolatey\nSet-ExecutionPolicy Bypass -Scope Process -Force; \n[System.Net.ServicePointManager]::SecurityProtocol = [System.Net.ServicePointManager]::SecurityProtocol -bor 3072; \niex ((New-Object System.Net.WebClient).DownloadString('https://chocolatey.org/install.ps1'))\n\n# Install dependencies using Chocolatey\nchoco install -y python3 wget gnupg2 xvfb unzip ffmpeg lame sox\n\n# Install Tesseract OCR\nchoco install -y tesseract\n$env:Path += \";C:\\Program Files\\Tesseract-OCR\"\n[Environment]::SetEnvironmentVariable(\"Path\", $env:Path, [EnvironmentVariableTarget]::Machine)\n\n# Download and install additional language data for Tesseract\n$tessDataUrl = \"https://github.com/tesseract-ocr/tessdata/raw/main/\"\n$tessDataDir = \"C:\\Program Files\\Tesseract-OCR\\tessdata\"\n$languages = @(\"eng\", \"deu\", \"fra\", \"spa\") # Add or remove languages as needed\n\nforeach ($lang in $languages) {\n $url = $tessDataUrl + $lang + \".traineddata\"\n $output = $tessDataDir + \"\\\" + $lang + \".traineddata\"\n Invoke-WebRequest -Uri $url -OutFile $output\n}\n\n# Refresh environment variables\n$env:Path = [System.Environment]::GetEnvironmentVariable(\"Path\",\"Machine\") + \";\" + [System.Environment]::GetEnvironmentVariable(\"Path\",\"User\")\n\n# Upgrade pip\npython -m pip install --upgrade pip\n\n# Install the Rezolve AI Ingestion package\npip install git+https://your-private-repo-url.com/rezolve-ai-ingestion.git\n\nWrite-Host \"Installation complete. Please restart your PowerShell.\"\n\n## Support\n\nFor support, please contact the internal development team at Rezolve.ai.\n\n## License\n\nThis project is proprietary and confidential. Unauthorized copying, transferring or reproduction of the contents of this project, via any medium is strictly prohibited.\n\nCopyright (c) 2024 Rezolve.ai. All Rights Reserved.\n",
"bugtrack_url": null,
"license": "Proprietary and Confidential",
"summary": "A private package for ingesting and processing SharePoint data with AI capabilities",
"version": "0.1.4",
"project_urls": {
"Homepage": "https://your-private-repo-url.com/rezolve-ai-ingestion",
"Repository": "https://your-private-repo-url.com/rezolve-ai-ingestion.git"
},
"split_keywords": [
"sharepoint",
" ai",
" ingestion",
" data processing",
" rezolve"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "ed4b8c6f33b7557d8c43a3b600b7a8c2a91ad8123571141ca3f08b5937e37168",
"md5": "65bf66f80015ae12436c37ede511235a",
"sha256": "330063204798011b5f0ae529242a71809f0f21cfaf0e7d221c31595026519320"
},
"downloads": -1,
"filename": "rezolve_ai_ingestion-0.1.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "65bf66f80015ae12436c37ede511235a",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 30212,
"upload_time": "2024-09-27T07:42:16",
"upload_time_iso_8601": "2024-09-27T07:42:16.233405Z",
"url": "https://files.pythonhosted.org/packages/ed/4b/8c6f33b7557d8c43a3b600b7a8c2a91ad8123571141ca3f08b5937e37168/rezolve_ai_ingestion-0.1.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "9e2e2db51cb373cb6ebc2d6f7df12c037ad9f99e5fcf2195a332d7c639c7c75b",
"md5": "9d2b5a2cb3768ed2464945d89f26e80d",
"sha256": "850fd3077c1f4d5f0a863c93bfe2fe7060765b6c69bebdd586fb36870004f9e1"
},
"downloads": -1,
"filename": "rezolve_ai_ingestion-0.1.4.tar.gz",
"has_sig": false,
"md5_digest": "9d2b5a2cb3768ed2464945d89f26e80d",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 25093,
"upload_time": "2024-09-27T07:42:17",
"upload_time_iso_8601": "2024-09-27T07:42:17.535931Z",
"url": "https://files.pythonhosted.org/packages/9e/2e/2db51cb373cb6ebc2d6f7df12c037ad9f99e5fcf2195a332d7c639c7c75b/rezolve_ai_ingestion-0.1.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-09-27 07:42:17",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "rezolve-ai-ingestion"
}
JSON