mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
aff44d0a98
Given that different models have very different latencies and pricings, it's benefitial to pass the information about the model that generated the response. Such information allows implementing custom callback managers and track usage and price per model. Addresses https://github.com/hwchase17/langchain/issues/1557. |
||
---|---|---|
.. | ||
__init__.py | ||
test_ai21.py | ||
test_aleph_alpha.py | ||
test_anthropic.py | ||
test_banana.py | ||
test_cerebrium.py | ||
test_cohere.py | ||
test_forefrontai.py | ||
test_gooseai.py | ||
test_huggingface_endpoint.py | ||
test_huggingface_hub.py | ||
test_huggingface_pipeline.py | ||
test_manifest.py | ||
test_modal.py | ||
test_nlpcloud.py | ||
test_openai.py | ||
test_petals.py | ||
test_promptlayer_openai.py | ||
test_propmptlayer_openai_chat.py | ||
test_self_hosted_llm.py | ||
test_stochasticai.py | ||
test_writer.py | ||
utils.py |