mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
0c6ed657ef
## Change Chain argument in client to accept a chain factory The `run_over_dataset` functionality seeks to treat each iteration of an example as an independent trial. Chains have memory, so it's easier to permit this type of behavior if we accept a factory method rather than the chain object directly. There's still corner cases / UX pains people will likely run into, like: - Caching may cause issues - if memory is persisted to a shared object (e.g., same redis queue) , this could impact what is retrieved - If we're running the async methods with concurrency using local models, if someone naively instantiates the chain and loads each time, it could lead to tons of disk I/O or OOM |
||
|---|---|---|
| .. | ||
| agents | ||
| callbacks | ||
| chains | ||
| chat_models | ||
| client | ||
| data | ||
| docstore | ||
| document_loader | ||
| evaluation | ||
| llms | ||
| memory | ||
| output_parsers | ||
| prompts | ||
| retrievers | ||
| tools | ||
| utilities | ||
| vectorstores | ||
| __init__.py | ||
| conftest.py | ||
| test_bash.py | ||
| test_depedencies.py | ||
| test_document_transformers.py | ||
| test_formatting.py | ||
| test_math_utils.py | ||
| test_python.py | ||
| test_schema.py | ||
| test_sql_database_schema.py | ||
| test_sql_database.py | ||
| test_text_splitter.py | ||