Another You’s chatbot system utilizes the secure and private Amazon Simple Storage Service (S3) to store our documents in the initial stage before further processing. S3 ensures encryption of all object uploads to all buckets, maintaining compliance with various programs like PCI-DSS, HIPAA/HITECH, FedRAMP, EU Data Protection Directive, and FISMA. This ensures that our data remains protected and compliant with regulatory requirements. Documents uploaded to Another You’s chatbot follow the SSE-S3 (Server-Side Encryption) protocol, allowing exclusive access to our team members and ensuring data confidentiality and privacy.
We utilize the secure and private Amazon Simple Storage Service (S3) to store our documents in the initial stage before further processing. S3 ensures encryption of all object uploads to all buckets, maintaining compliance with various programs like PCI-DSS, HIPAA/HITECH, FedRAMP, EU Data Protection Directive, and FISMA. This ensures that our data remains protected and compliant with regulatory requirements. Documents uploaded follow the SSE-S3 (Server-Side Encryption) protocol, allowing exclusive access our team members, ensuring data confidentiality and privacy.
Embeddings
Embeddings are essentially a representation of the uploaded data in the form of vectors (lists of numbers). Since the data provided is unstructured, converting it into embeddings allows for faster retrievals and semantic search.
For storing these vectors or embeddings, the Another You chatbot relies on Pinecone, a secure vector database trusted by some of the largest enterprises.
Pinecone offers robust security features like:
- SOC2 Type II certification
- GDPR-Compliance
- Routine Penetration Tests to check for vulnerabilities.
- Isolated Kubernetes containers on fully managed and secure AWS infrastructure for storing data.
Model
Another You’s chatbot AI leverages OpenAI’s GPT models, including GPT-3.5, GPT-3.5 16K, and GPT-4, to generate responses. Due to resource limitations, these models are not hosted on our native servers. Instead, they utilize the APIs provided by OpenAI (also used for creating embeddings for your documents and queries). When generating responses, only the specific portion of data relevant to the question asked is sent in the request, rather than all the documents. This approach ensures efficient processing and data integrity and minimizes unnecessary data transfers. An additional security mechanism provided by the API is that your data will not be used to train any existing or new language models. This ensures that your data remains restricted to your bot and is not utilized for model training purposes.
Starting on March 1, 2023, we are making two changes to our data usage and retention policies:
1. OpenAI will not use data submitted by customers via our API to train or improve the models unless you explicitly decide to share your data with us for this purpose. You can opt-in to share data.
2. Any data sent through the API will be retained for abuse and misuse monitoring purposes for a maximum of 30 days, after which it will be deleted (unless otherwise required by law).
