fix(docs): correct embeddings provider count and guard the table against drift
The refreshed provider table said 12 embedders; EmbedderFactory registers 11. The other three rows were right, so the table drifted silently again inside the commit that was fixing it drifting. Add tests/test_agents_md_provider_counts.py, which parses the AGENTS.md provider table and asserts each documented count equals len(<Factory>.provider_to_class). Verified it fails on the 12 and passes on 11.
This commit is contained in:
@@ -342,7 +342,7 @@ The SDK uses a consistent plugin architecture across 4 categories. Each category
|
||||
|----------|-------|---------|
|
||||
| **LLMs** | 18 | OpenAI, Anthropic, AWS Bedrock, Azure OpenAI, Gemini, Groq, Ollama, Together, DeepSeek, vLLM, LiteLLM, LM Studio, xAI |
|
||||
| **Vector Stores** | 25 | Qdrant, Pinecone, Chroma, Weaviate, Milvus, MongoDB, Redis, Elasticsearch, pgvector, Supabase, Faiss, S3 Vectors |
|
||||
| **Embeddings** | 12 | OpenAI, Azure OpenAI, Gemini, HuggingFace, FastEmbed, Together, AWS Bedrock, Ollama, Vertex AI |
|
||||
| **Embeddings** | 11 | OpenAI, Azure OpenAI, Gemini, HuggingFace, FastEmbed, Together, AWS Bedrock, Ollama, Vertex AI |
|
||||
| **Rerankers** | 5 | Cohere, HuggingFace, LLM-based, Sentence Transformer, Zero Entropy |
|
||||
|
||||
### Two Usage Modes
|
||||
|
||||
@@ -0,0 +1,37 @@
|
||||
"""Drift test: the provider counts in AGENTS.md must match the factory registries."""
|
||||
|
||||
import re
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
from mem0.utils.factory import (
|
||||
EmbedderFactory,
|
||||
LlmFactory,
|
||||
RerankerFactory,
|
||||
VectorStoreFactory,
|
||||
)
|
||||
|
||||
AGENTS_MD = Path(__file__).resolve().parents[1] / "AGENTS.md"
|
||||
|
||||
ROW_TO_FACTORY = {
|
||||
"LLMs": LlmFactory,
|
||||
"Vector Stores": VectorStoreFactory,
|
||||
"Embeddings": EmbedderFactory,
|
||||
"Rerankers": RerankerFactory,
|
||||
}
|
||||
|
||||
|
||||
def _documented_counts() -> dict[str, int]:
|
||||
rows = re.findall(r"^\|\s*\*\*(.+?)\*\*\s*\|\s*(\d+)\s*\|", AGENTS_MD.read_text(), re.M)
|
||||
return {name: int(count) for name, count in rows}
|
||||
|
||||
|
||||
@pytest.mark.parametrize("row_name,factory", ROW_TO_FACTORY.items())
|
||||
def test_documented_count_matches_registry(row_name, factory):
|
||||
documented = _documented_counts()
|
||||
assert row_name in documented, f"AGENTS.md provider table has no {row_name!r} row"
|
||||
assert documented[row_name] == len(factory.provider_to_class), (
|
||||
f"AGENTS.md says {documented[row_name]} {row_name} but "
|
||||
f"{factory.__name__}.provider_to_class has {len(factory.provider_to_class)}"
|
||||
)
|
||||
Reference in New Issue
Block a user