MistralAIEmbeddings retry decorator catches wrong exception type for rate limiting

[Gero-Gi]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

from langchain_mistralai import MistralAIEmbeddings
    embeddings = MistralAIEmbeddings(
    model="mistral-embed",
    mistral_api_key="your-api-key",
    wait_time=30 # Should be used for rate limit retries
)

Making multiple requests in quick succession triggers rate limits

for i in range(10):
    # When hitting rate limits, raises httpx.HTTPStatusError without retrying
    embeddings.embed_query("Test string")

Error Message and Stack Trace (if applicable)

File "/usr/local/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py", line 286, in invoke
self.generate_prompt(
File "/usr/local/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py", line 786, in generate_prompt
return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)
File "/usr/local/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py", line 643, in generate
raise e
File "/usr/local/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py", line 633, in generate
self._generate_with_cache(
File "/usr/local/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py", line 851, in _generate_with_cache
result = self._generate(
File "/usr/local/lib/python3.10/site-packages/langchain_mistralai/chat_models.py", line 545, in _generate
response = self.completion_with_retry(
File "/usr/local/lib/python3.10/site-packages/langchain_mistralai/chat_models.py", line 464, in completion_with_retry
rtn = _completion_with_retry(**kwargs)
File "/usr/local/lib/python3.10/site-packages/langchain_mistralai/chat_models.py", line 461, in _completion_with_retry
_raise_on_error(response)
File "/usr/local/lib/python3.10/site-packages/langchain_mistralai/chat_models.py", line 170, in _raise_on_error
raise httpx.HTTPStatusError(
httpx.HTTPStatusError: Error response 429 while fetching https://api.mistral.ai/v1/chat/completions: {"message":"Requests rate limit exceeded"}

Description

The MistralAIEmbeddings class currently uses a retry decorator that only catches httpx.TimeoutException, but according to the documentation, it should be handling rate limit (429) errors using the wait_time parameter.

Current Behavior

• The retry decorator only catches httpx.TimeoutException
• When hitting rate limits (429 errors), the code raises an httpx.HTTPStatusError without retrying
• The wait_time parameter is documented as "The number of seconds to wait before retrying a request in case of 429 error" but isn't actually used for this purpose

Expected Behavior

• The retry decorator should catch httpx.HTTPStatusError to handle 429 rate limit responses
• When receiving a 429 error, it should wait for wait_time seconds before retrying
• This matches the documented behavior of the wait_time parameter

System Info

System Information

OS: Linux
OS Version: #49~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Nov 6 17:42:15 UTC 2
Python Version: 3.10.16 (main, Dec 24 2024, 22:23:12) [GCC 12.2.0]

Package Information

langchain_core: 0.3.29
langchain: 0.3.14
langchain_community: 0.3.14
langsmith: 0.2.10
langchain_mistralai: 0.2.4
langchain_ollama: 0.2.2
langchain_qdrant: 0.2.0
langchain_text_splitters: 0.3.5
langchainhub: 0.1.21

Optional packages not installed

langserve

Other Dependencies

aiohttp: 3.11.11
async-timeout: 4.0.3
dataclasses-json: 0.6.7
fastembed: Installed. No version info available.
httpx: 0.27.2
httpx-sse: 0.4.0
jsonpatch: 1.33
langsmith-pyo3: Installed. No version info available.
numpy: 1.26.4
ollama: 0.4.5
orjson: 3.10.13
packaging: 24.2
pydantic: 2.9.2
pydantic-settings: 2.7.1
PyYAML: 6.0.2
qdrant-client: 1.12.2
requests: 2.32.3
requests-toolbelt: 1.0.0
SQLAlchemy: 2.0.36
tenacity: 9.0.0
tokenizers: 0.21.0
types-requests: 2.32.0.20241016
typing-extensions: 4.12.2
zstandard: Installed. No version info available.