mirror of
https://github.com/hwchase17/langchain.git
synced 2025-06-02 04:58:46 +00:00
305d74c67a
**Description:** Currently, `CacheBackedEmbeddings` computes vectors for *all* uncached documents before updating the store. This pull request updates the embedding computation loop to compute embeddings in batches, updating the store after each batch. I noticed this when I tried `CacheBackedEmbeddings` on our 30k document set and the cache directory hadn't appeared on disk after 30 minutes. The motivation is to minimize compute/data loss when problems occur: * If there is a transient embedding failure (e.g. a network outage at the embedding endpoint triggers an exception), at least the completed vectors are written to the store instead of being discarded. * If there is an issue with the store (e.g. no write permissions), the condition is detected early without computing (and discarding!) all the vectors. **Issue:** Implements enhancement #18026. **Testing:** I was unable to run unit tests; details in [this post](https://github.com/langchain-ai/langchain/discussions/15019#discussioncomment-8576684). --------- Signed-off-by: chrispy <chrispy@synopsys.com> Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com> |
||
|---|---|---|
| .. | ||
| _api | ||
| beta | ||
| callbacks | ||
| document_loaders | ||
| documents | ||
| embeddings | ||
| example_selectors | ||
| language_models | ||
| load | ||
| messages | ||
| output_parsers | ||
| outputs | ||
| prompts | ||
| pydantic_v1 | ||
| runnables | ||
| tracers | ||
| utils | ||
| __init__.py | ||
| agents.py | ||
| caches.py | ||
| chat_history.py | ||
| chat_sessions.py | ||
| env.py | ||
| exceptions.py | ||
| globals.py | ||
| memory.py | ||
| prompt_values.py | ||
| py.typed | ||
| retrievers.py | ||
| stores.py | ||
| sys_info.py | ||
| tools.py | ||
| vectorstores.py | ||