riivault_

langchain

pypi package · declared by 89 of 2,343 sampled repositories · graph computed 2026-08-24

Counted from the runtime dependencies public repositories declare — not the resolved tree. A transitive dependency is a consequence; a declared one is a choice. Development dependencies are excluded because they repeat across every project in a language regardless of what is being built.

Declared with

ranked by association, not by count
Declared withRepositoriesvs chance
langchain-openai46 of 2,3430.84
langchain-community35 of 2,3430.83
langchain-core26 of 2,3430.67
langchain-ollama11 of 2,3430.66
langchain-google-genai13 of 2,3430.63
langchain-huggingface8 of 2,3430.61
langgraph18 of 2,3430.60
unstructured8 of 2,3430.59
langchain-anthropic10 of 2,3430.57
chromadb14 of 2,3430.57
sentence-transformers17 of 2,3430.50
streamlit10 of 2,3430.48
pypdf9 of 2,3430.42
nltk9 of 2,3430.41
python-dotenv32 of 2,3430.37
tiktoken14 of 2,3430.34
openai26 of 2,3430.33
pandas21 of 2,3430.32
beautifulsoup49 of 2,3430.27
datasets9 of 2,3430.27

Every pair above is counted from the same evidence: repo manifest.

Used instead

candidates · shares a neighbourhood and refuses to co-occur

No alternative measured. A pair qualifies only if it shares a neighbourhood and then fails to appear together against an expectation that it would — and almost everything that shares a neighbourhood does appear together. That is the test working, not a gap in the data: similarity alone would list this tool’s closest neighbours as alternatives, and most of them are things it is used with.