Files

Mahdi Bazrafshan 6c9cebaaa0 docs(research): add farsi embedding model research knowledge base

Body:
        Why:
        - Insurance RAG pipeline needs Farsi-optimized embeddings
        - Current local baseline (Nomic Embed) is English-only

        Changes:
        - 8 cloud model profiles with curl + python test commands
        - 5 local model profiles with VRAM, serving platform notes
        - Persian benchmark landscape (MIRACL-Fa, mMARCO, FaMTE, MTEB)
        - Decision report with ranked options and recommendations
        - Full comparison table (15 models × 10 columns)

        Impact:
        - Knowledge base for embedding model selection
        - Top picks: BGE-M3 (local), Cohere embed-v4.0 (cloud)
        - Critical: Nomic Embed must be replaced (English-only)

2026-07-20 15:00:11 +03:30

2.8 KiB

Raw Blame History

last_updated, tags, source

last_updated

Embedding Models Research — Farsi Insurance RAG

Date: July 20, 2026 Context: LangGraph + Qdrant RAG pipeline for insurance domain. Only language is Farsi (Persian). Goal: Find Farsi-strong embedding models that outperform OpenAI on top-K retrieval.

Quick Start

Read the big picture: overview/big-picture.md — full comparison table + recommendations
Read the decision report: decision-report/README.md — ranked options with pros/cons
Test cloud models: Each model file has curl + Python test commands
Replace Nomic: Deploy BGE-M3 on Ollama (see bge-m3.md)

Files

Cloud Models

Model	Price	File
OpenAI text-embedding-3-large	$0.13/1M	openai.md
OpenAI text-embedding-3-small	$0.02/1M	openai.md
Cohere embed-v4.0	Enterprise	cohere.md
Voyage voyage-4-large	$0.12/1M	voyage.md
Voyage voyage-4	$0.06/1M	voyage.md
Google Gemini Embedding	$0.15/1M	google.md
Google text-embedding-004	~$0.10/1M	google.md
Jina jina-embeddings-v3	~$0.02/1M	jina.md

Local Models

Model	VRAM	Farsi	File
BGE-M3 ⭐	1.1 GB	✅	bge-m3.md
gte-multilingual-base	610 MB	✅	gte-multilingual.md
multilingual-E5-large	1.1 GB	✅	mE5-large.md
Nomic Embed ⚠️	274 MB	❌ EN only	nomic.md

Cross-Cutting

Topic	File
Comparison table	overview/big-picture.md
Decision report	decision-report/README.md
Persian benchmarks	benchmarks/README.md

Critical Finding

Nomic Embed v1.5 (current local baseline) is English-only. It does not support Farsi. Replace with BGE-M3 immediately.

Top Recommendations

Decision	Winner	Why
Local model	BGE-M3	Triple-mode (dense+sparse+ColBERT), Farsi, 1.1 GB VRAM, MIT
Cloud model	Cohere embed-v4.0	Strongest Farsi, 512K context, enterprise pricing
Budget cloud	Voyage voyage-4-large	$0.12/1M, 200M free tokens
Serving platform	Ollama	Already deployed, BGE-M3 available

TODO

Deploy BGE-M3 on Ollama
Run 100-question eval set against all candidates
Benchmark on MIRACL-Farsi
Calculate monthly cloud cost at production volume
Verify Cohere enterprise pricing feasibility

2.8 KiB Raw Blame History