mirror of
https://github.com/hwchase17/langchain
synced 2024-11-10 01:10:59 +00:00
cfecbda48b
### Issue
Recently, the new `allow_dangerous_deserialization` flag was introduced
for preventing unsafe model deserialization that relies on pickle
without user's notice (#18696). Since then some LLMs like Databricks
requires passing in this flag with true to instantiate the model.
However, this breaks existing functionality to loading such LLMs within
a chain using `load_chain` method, because the underlying loader
function
[load_llm_from_config](
|
||
|---|---|---|
| .. | ||
| adapters | ||
| agent_toolkits | ||
| callbacks | ||
| chat_loaders | ||
| chat_message_histories | ||
| chat_models | ||
| docstore | ||
| document_compressors | ||
| document_loaders | ||
| document_transformers | ||
| embeddings | ||
| example_selectors | ||
| graphs | ||
| indexes | ||
| llms | ||
| output_parsers | ||
| retrievers | ||
| storage | ||
| tools | ||
| utilities | ||
| utils | ||
| vectorstores | ||
| __init__.py | ||
| cache.py | ||
| py.typed | ||