Sold by: MphasisÂ
Deployed on AWS
Improve searching through your knowledge base by adapting embeddings to your domain and data using Generative AI.
Overview
Systems can search through similar content through vector similarity computations. This solution uses Generative AI to help customize the LLM model that embeds the vector to understand the nature of questions and domain semantics. Alignment of embeddings using custom finetuned LLMs helps improve search results which is observed by improved rankings of relevant content. The input is a CSV with questions and corresponding answers - for example a FAQ dataset. The embedding model is fine-tuned on this dataset. At the time of inference this trained model can be used to embed any text content. This means the trained foundational model can be used to vectorize the final desired corpus and incoming queries for search. The solution leverages the current state of the art techniques in the domain of generative AI to finetune custom LLM models to generate the right set of embeddings.
Highlights
- The solution is intended to be used as part of a search and retrieval workflow. The fine-tuned LLM model can be used to embed your documents to a vector database and vectorize incoming search queries.
- The solution takes input in the form of simple Q&A pairs. This helps the LLM align with the type of questions that will be posed to the system in production.
- Mphasis DeepInsights is a cloud-based cognitive computing platform that offers data extraction & predictive analytics capabilities. Need customized Machine Learning and Deep Learning solutions? Get in touch!
Details
Sold by
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost |
|---|---|---|
ml.m5.2xlarge Inference (Batch) Recommended | Model inference on the ml.m5.2xlarge instance type, batch mode | $3.00/host/hour |
ml.g4dn.xlarge Training Recommended | Algorithm training on the ml.g4dn.xlarge instance type | $10.00/host/hour |
ml.m4.4xlarge Inference (Batch) | Model inference on the ml.m4.4xlarge instance type, batch mode | $3.00/host/hour |
ml.m5.4xlarge Inference (Batch) | Model inference on the ml.m5.4xlarge instance type, batch mode | $3.00/host/hour |
ml.m4.16xlarge Inference (Batch) | Model inference on the ml.m4.16xlarge instance type, batch mode | $3.00/host/hour |
ml.p3.16xlarge Inference (Batch) | Model inference on the ml.p3.16xlarge instance type, batch mode | $3.00/host/hour |
ml.m4.2xlarge Inference (Batch) | Model inference on the ml.m4.2xlarge instance type, batch mode | $3.00/host/hour |
ml.c5.2xlarge Inference (Batch) | Model inference on the ml.c5.2xlarge instance type, batch mode | $3.00/host/hour |
ml.p3.2xlarge Inference (Batch) | Model inference on the ml.p3.2xlarge instance type, batch mode | $3.00/host/hour |
ml.c4.2xlarge Inference (Batch) | Model inference on the ml.c4.2xlarge instance type, batch mode | $3.00/host/hour |
Vendor refund policy
Currently we do not support refunds, but you can cancel your subscription to the service at any time.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA)Â .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker algorithm
An Amazon SageMaker algorithm is a machine learning model that requires your training data to make predictions. Use the included training algorithm to generate your unique model artifact. Then deploy the model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
This is the latest version.
Additional details
Inputs
- Summary
The input to training pipeline is a "train.zip" file which contains train.csv file(with columns as "Question" and "Answer") and a user_input json file having hyper parmeters ({"BATCH_SIZE":10,"EPOCHS":5})
- Input MIME type
- application/zip, application/gzip, text/plain
https://github.com/Mphasis-ML-Marketplace/Embedding-LLM-finetuning-for-search/blob/main/Input/train.zip
https://github.com/Mphasis-ML-Marketplace/Embedding-LLM-finetuning-for-search/tree/main/Input
Resources
Vendor resources
Support
Vendor support
For any assistance reach out to us at:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Solution enhances the search for specific business processes by accounting for language and intents of different user roles in the domain.
Text embedding model optimized for general-purpose (including multilingual) retrieval/search and AI applications. 32K context length.
New State-of-the-Art Multilingual Embeddings With Task LoRA
State-of-the-art text embedding model with the best general-purpose and multilingual retrieval quality. 32K context length.
Use Cohere's multilingual embedding model to map text to a semantic vector space, positioning text with a similar meaning in close proximity
Text embedding model optimized for legal retrieval and AI applications. Tops the MTEB leaderboard for legal retrieval. 16K context length.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.