Serverless-Retrieval-Augmented-Generation-RAG-on-AWS

Serverless-Retrieval-Augmented-Generation-RAG-on-AWS copied to clipboard

Architecture: evaluate VPC endpoints and network topology impacts

[]

We want to evaluate what's the (performance gain+cost saving) vs (cold-start performance impact+operational overhead) of introducing the usage of VPC endpoints (S3, Bedrock). It could potentially suck because customers would...

giusedroid

Chore: bump up dependencies

[]

We have (at the time of writing) 5 open PRs for dependency management. We should address each of them independently, run acceptance tests, and merge.

giusedroid

Load Test: concurrent usage

[]

right now we have limited the execution of the ingestion function to 1. [LanceDB has a native lock system based on DynamoDB locks](https://lancedb.github.io/lance/read_and_write.html#concurrent-writer-on-s3-using-dynamodb) currently in beta. We should experiment with...

giusedroid

Load Test: scale to billions of vectors

[]

- retrieval performance impact when getting to billions of vectors - any network bottlenecks? - what's the maximum number of vector per users per knowledge-base we can whitstand?

giusedroid

Load Test : move knowledge base to S3Express

[]

- Measure what's the gain on latency - Any fundamental architectural changes that would make it less serverless? - impact on costs? - impact on resilience?

giusedroid

Bump tqdm from 4.66.1 to 4.66.3 in /lambda/document-processor

[]

Bumps [tqdm](https://github.com/tqdm/tqdm) from 4.66.1 to 4.66.3. Release notes Sourced from tqdm's releases. tqdm v4.66.3 stable cli: eval safety (fixes CVE-2024-34062, GHSA-g7vv-2v7x-gj9p) tqdm v4.66.2 stable pandas: add DataFrame.progress_map (#1549) notebook: fix...

dependabot[bot]

Bump requests from 2.31.0 to 2.32.2 in /lambda/document-processor

[]

Bumps [requests](https://github.com/psf/requests) from 2.31.0 to 2.32.2. Release notes Sourced from requests's releases. v2.32.2 2.32.2 (2024-05-21) Deprecations To provide a more stable migration for custom HTTPAdapters impacted by the CVE changes...

dependabot[bot]

Bump idna from 3.4 to 3.7 in /lambda/document-processor

[]

Bumps [idna](https://github.com/kjd/idna) from 3.4 to 3.7. Release notes Sourced from idna's releases. v3.7 What's Changed Fix issue where specially crafted inputs to encode() could take exceptionally long amount of time...

dependabot[bot]

Bump aiohttp from 3.9.4 to 3.10.11 in /lambda/document-processor

[]

Bumps [aiohttp](https://github.com/aio-libs/aiohttp) from 3.9.4 to 3.10.11. Release notes Sourced from aiohttp's releases. 3.10.11 Bug fixes Authentication provided by a redirect now takes precedence over provided auth when making requests with...

dependabot[bot]

Bump langchain from 0.0.337 to 0.3.7 in /lambda/document-processor

[]

Bumps [langchain](https://github.com/langchain-ai/langchain) from 0.0.337 to 0.3.7. Release notes Sourced from langchain's releases. langchain-core==0.3.7 Changes since langchain-core==0.3.6 core[patch]: Release 0.3.7 (#27004) core[patch]: fix structured prompt template format (#27003) core: Add ruff...

dependabot[bot]