Safely load data in Gen AI apps

by daxa.ai

Safely load and retrieve data
in your Gen AI applications

What is Pebblo?

Pebblo enables developers to safely load and retrieve data to promote their Gen AI app to deployment without worrying about the organization’s compliance and security requirements. The Pebblo SafeLoader identifies semantic topics and entities found in the loaded data and the Pebblo SafeRetriever (coming soon on this page) enforces identity and semantic controls on the retrieved context. The results are summarized on the UI or a PDF report.

Highlights

Identify semantic topics and entities in your data loaded in RAG applications

Prevent restricted data access by unauthorized RAG app users

Accelerate time-to-production by effortlessly meeting your organization’s data compliance requirements

Comply with regulations such as the EU AI Act with custom reports and data records

Support for a wide range of Gen AI development frameworks and data loaders

Flexible reporting options on the UI, PDF, JSON and more

Pebblo SafeLoader

Check on Github

[data-wf-bgvideo-fallback-img] { display: none; } @media (prefers-reduced-motion: reduce) { [data-wf-bgvideo-fallback-img] { position: absolute; z-index: -100; display: inline-block; height: 100%; width: 100%; object-fit: cover; } }

Lorm ipsum reviews tools you need simplicity

Pebblo enables developers to safely load data and promote their Gen AI app to deployment without worrying about the organization’s compliance.

Join the conversation

Pebblo enables Pebblo developers to safely load data @pebblo and promote their Gen AI app to deployment without worrying about the organization’s compliance and # pebblo security requirements.

John Doe

Sr. Product Manager

Pebblo enables Pebblo developers to safely load data @pebblo and promote their Gen AI app to deployment without worrying about the organization’s compliance and # pebblo security requirements.

John Doe

Sr. Product Manager

Pebblo enables Pebblo developers to safely load data @pebblo and promote their Gen AI app to deployment without worrying about the organization’s compliance and # pebblo security requirements.

John Doe

Sr. Product Manager

Steps to deploy

1. Install and Start Pebblo daemon

Install Pebblo Server

pip install pebblo --extra-index-url https://packages.daxa.ai/simple/

Run Pebblo daemon

pebblo

2. Change your code and deploy the app

from langchain.document_loaders.csv_loader import CSVLoader
from langchain_community.document_loaders.pebblo import PebbloSafeLoader
‍
loader = PebbloSafeLoader(
          CSVLoader(file_path),
          name="acme-corp-rag-1", # App name (Mandatory)
          owner="Joe Smith", # Owner (Optional)
          description="Support RAG app",# Description(Optional)
)
‍
documents = loader.load()
vectordb = Chroma.from_documents(documents, OpenAIEmbeddings())

3. Get Data reports (UI or PDF)

Pebblo Safe Retriever

Check on Github

Lorm ipsum reviews tools you need simplicity

Pebblo enables developers to safely load data and promote their Gen AI app to deployment without worrying about the organization’s compliance.

Join the conversation

Pebblo enables Pebblo developers to safely load data @pebblo and promote their Gen AI app to deployment without worrying about the organization’s compliance and # pebblo security requirements.

John Doe

Sr. Product Manager

Pebblo enables Pebblo developers to safely load data @pebblo and promote their Gen AI app to deployment without worrying about the organization’s compliance and # pebblo security requirements.

John Doe

Sr. Product Manager

Pebblo enables Pebblo developers to safely load data @pebblo and promote their Gen AI app to deployment without worrying about the organization’s compliance and # pebblo security requirements.

John Doe

Sr. Product Manager

Steps to deploy

1. Add Identity-aware Safe Loader

self.loader = PebbloSafeLoader(
GoogleDriveLoader(
folder_id=folder_id,
  token_path="./google_token.json",
  recursive=True,
  file_loader_cls=UnstructuredFileIOLoader,
  file_loader_kwargs={"mode": "elements"},
  load_auth=True,
),
name=self.app_name, # App name (Mandatory)
owner="Joe Smith", # Owner (Optional)
description="Identity enabled SafeLoader and SafeRetrival app using Pebblo", # Description (Optional)
)

2. Add SafeRetrieval code

self.retrieval_chain = PebbloRetrievalQA.from_chain_type(     llm=self.llm,
    app_name=self.retrieval_app_name,
    owner="Joe Smith",
    description="Identity enabled SafeRetrival app using Pebblo",     chain_type="stuff",
    retriever=self.vectordb.as_retriever(),
    verbose=True,
)
auth_context = {
    "user_id": "joe@acme.io",
    "user_auth": [
        "joe@acme.io",
        "hr-group@acme.io",
        "us-employees-group@acme.io",
],
}
self.retrieval_chain.invoke({"auth_context": auth_context})

3. Get User Data Report