mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
76a193decc
LLMs struggle with Graph RAG, because it's different from vector RAG in a way that you don't provide the whole context, only the answer and the LLM has to believe. However, that doesn't really work a lot of the time. However, if you wrap the context as function response the accuracy is much better. btw... `union[LLMChain, Runnable]` is linting fun, that's why so many ignores |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| arangodb.py | ||
| base.py | ||
| cypher_utils.py | ||
| cypher.py | ||
| falkordb.py | ||
| gremlin.py | ||
| hugegraph.py | ||
| kuzu.py | ||
| nebulagraph.py | ||
| neptune_cypher.py | ||
| neptune_sparql.py | ||
| ontotext_graphdb.py | ||
| prompts.py | ||
| sparql.py | ||