Add production RAG service: FastAPI + Fireworks embeddings + pgvector - #556
Open
steps-re wants to merge 2 commits into
Open
Add production RAG service: FastAPI + Fireworks embeddings + pgvector#556steps-re wants to merge 2 commits into
steps-re wants to merge 2 commits into
Conversation
- FastAPI service using Fireworks AI embeddings and chat completions - pgvector retrieval with Pydantic citation models - async batch embedding, docker-compose, cost comparison vs OpenAI Signed-off-by: Mike German <mike@stepsventures.com>
Signed-off-by: Mike German <mike@stepsventures.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
A production-shaped RAG service built on Fireworks AI: FastAPI + Fireworks embeddings + pgvector retrieval + Pydantic-structured citations.
nomic-ai/nomic-embed-text-v1.5pgvectorwith an IVFFlat cosine index for retrievaldocker-compose.ymlbrings uppgvector/postgres(health-checked) and the app in one command/health,/query,/ingestendpointstext-embedding-3-small/gpt-4oVerified
init_db(table + IVFFlat cosine index), insert documents with real embeddings, then retrieve — a "how do plants make energy from sunlight?" query returns the photosynthesis document first (cosine ~0.82), correctly ranked above unrelated documents./healthresponds, Pydantic models validate;ruffclean.