Quickstart with Our Gateway

Warning: This guide is designed for discovery and testing. For production, follow the hardening and credential delegation guides in Configure External or Delegated Credentials for Cloud Storage.

This quickstart focuses on AWS-first examples for both Cloud Storage and AI LLM workflows. You can adapt the same setup pattern to other compatible providers supported by Flashgate.

Use these two micro tutorials:

• Start Quickly with Cloud Storage

• Start Quickly with AI LLM

---

Start Quickly with Cloud Storage

Follow this flow to upload your first object through Flashgate.

Prerequisites

• Python 3.9+

• boto3 installed

• A Flashgate workspace with access to Storage, Repositories, and API Keys

• An AWS S3 bucket you can connect (direct credentials or delegated access)

1

Sign in

Sign in at platform.flashback.tech with your account.

If you do not have an account yet, you can request a demo.

2

Configure your first bucket

You can use delegated access (recommended) or direct credentials for a quick test.

• Go to Storage → Buckets.

• Click Add Bucket.

• Fill in the bucket form:

  • Name: My First Bucket

  • Storage Type: S3

  • Bucket: your exact AWS S3 bucket name

  • Access Key / Secret Key: AWS access key pair (or delegated role info)

  • Endpoint: leave empty for AWS, or set custom S3 endpoint

  • Region: required when endpoint is empty

• Click Create.

Detailed guide: Configure a Bucket.

3

Create a repository

• Go to Repositories.

• Click Add Repository.

• Fill:

  • Name: my-first-s3-repository

  • API Type: S3

• In Storage Buckets, attach My First Bucket.

• Click Create.

Detailed guide: Create a Repository.

4

Generate an API key

In your repository:

• Open Inventory in Repositories. Choose your newly created repository.

• Look for the API Key Table,and Click Add, and select Buckets.

• Set a label such as quickstart-write.

• Choose access mode WRITE/READ/ADMIN (read+write).

• Copy the secret immediately (it is shown once).

5

Run storage snippets (reviewed)

Install dependency:

pip install boto3

Create a shared config file:

# flashgate_s3_config.py
import os
import boto3
from botocore.client import Config

FLASHGATE_S3_ENDPOINT = os.environ["FLASHGATE_S3_ENDPOINT"]
FLASHGATE_S3_KEY_ID = os.environ["FLASHGATE_S3_KEY_ID"]
FLASHGATE_S3_SECRET = os.environ["FLASHGATE_S3_SECRET"]

session = boto3.session.Session(
    aws_access_key_id=FLASHGATE_S3_KEY_ID,
    aws_secret_access_key=FLASHGATE_S3_SECRET,
)

s3_client = session.client(
    service_name="s3",
    endpoint_url=FLASHGATE_S3_ENDPOINT,
    config=Config(signature_version="s3v4"),
)

List buckets exposed by your repository:

# list_buckets.py
from flashgate_s3_config import s3_client

response = s3_client.list_buckets()
print("Buckets available through Flashgate:")
for bucket in response.get("Buckets", []):
    print(f" - {bucket['Name']}")

Upload a file:

# upload_file.py
import os
from pathlib import Path
from flashgate_s3_config import s3_client

bucket_name = os.environ["FLASHGATE_BUCKET_NAME"]
file_path = Path(os.environ["LOCAL_FILE_PATH"])
object_key = file_path.name

s3_client.upload_file(
    Filename=str(file_path),
    Bucket=bucket_name,
    Key=object_key,
)

print(f"Uploaded '{object_key}' to bucket '{bucket_name}'.")

Example environment variables:

export FLASHGATE_S3_ENDPOINT="https://s3-us-east-1.aws.flashback.tech"
export FLASHGATE_S3_KEY_ID="<your-repository-api-key-id>"
export FLASHGATE_S3_SECRET="<your-repository-api-secret>"
export FLASHGATE_BUCKET_NAME="<bucket-attached-to-repository>"
export LOCAL_FILE_PATH="./sample.txt"

---

Start Quickly with AI LLM

This quickstart shows an AWS-oriented AI setup with Flashgate acting as the unified gateway.

Prerequisites

• Python 3.9+

• openai SDK installed

• A Flashgate workspace with access to AI LLM, Repositories, and API Keys

• AWS model access enabled in your account (for example via Amazon Bedrock)

1

Add an AI LLM provider (AWS)

• Go to AI → AI LLM.

• Click Add AI LLM.

• Select AI LLM Type: AWS.

• Fill:

  • Configuration Name: aws-llm-primary

  • API Endpoint: your AWS-compatible endpoint used by Flashgate

  • API Secret: credential/token used by that endpoint

  • API Key: fill only if your endpoint requires it

• Click Create configuration.

Detailed guide: Configure an AI LLM.

2

Create an AI repository

• Go to Repositories → Add Repository.

• Set:

  • Name: my-first-ai-repository

  • API Type: AI

• In provider/resource selection, attach aws-llm-primary.

• Save the repository.

3

Generate an AI API key

In the AI repository:

• Open Inventory in Repositories. Choose your newly created repository.

• Look for the API Key Table,and Click Add, and select AI LLMs.

• Set a label such as quickstart-write.

• Copy and store the secret immediately.

4

Run AI snippets (reviewed)

Install dependency:

pip install openai

Call the repository endpoint with the OpenAI-compatible SDK:

# ai_prompt.py
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["FLASHGATE_AI_API_KEY"],
    base_url=os.environ["FLASHGATE_AI_BASE_URL"],
)

response = client.chat.completions.create(
    model=os.environ.get("FLASHGATE_AI_MODEL", "anthropic.claude-3-5-sonnet"),
    messages=[
        {"role": "system", "content": "You are a concise cloud assistant."},
        {"role": "user", "content": "Summarize the value of a unified AI gateway in 3 bullets."},
    ],
    temperature=0.2,
)

print(response.choices[0].message.content)

Example environment variables:

export FLASHGATE_AI_BASE_URL="https://api.flashback.tech/ai/openai"
export FLASHGATE_AI_API_KEY="<your-ai-repository-api-key>"
export FLASHGATE_AI_MODEL="anthropic.claude-3-5-sonnet"

Model identifiers depend on what your AWS-backed configuration exposes through Flashgate. If a model is rejected, list or validate available models in your workspace and update FLASHGATE_AI_MODEL.