Merge pull request #14700 from BerriAI/litellm_contributor_prs_09_18_2025_p2

Update Bedrock documentation for Titan V2 encoding_format support + Anthropic - account for 1h vs. 5m cache creation token cost difference + UI - add langsmith_sampling_rate as a dynamic param

Author: krrishdholakia

docs/my-website/docs/providers/bedrock.md

@@ -1822,6 +1822,59 @@ Here's an example of using a bedrock model with LiteLLM. For a complete list, re
 | Mixtral 8x7B Instruct      | `completion(model='bedrock/mistral.mixtral-8x7b-instruct-v0:1', messages=messages)`   | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`, `os.environ['AWS_REGION_NAME']` |
 
 
+## Bedrock Embedding
+
+### API keys
+This can be set as env variables or passed as **params to litellm.embedding()**
+```python
+import os
+os.environ["AWS_ACCESS_KEY_ID"] = ""        # Access key
+os.environ["AWS_SECRET_ACCESS_KEY"] = ""    # Secret access key
+os.environ["AWS_REGION_NAME"] = ""           # us-east-1, us-east-2, us-west-1, us-west-2
+```
+
+### Usage
+```python
+from litellm import embedding
+response = embedding(
+    model="bedrock/amazon.titan-embed-text-v1",
+    input=["good morning from litellm"],
+)
+print(response)
+```
+
+#### Titan V2 - encoding_format support
+```python
+from litellm import embedding
+# Float format (default)
+response = embedding(
+    model="bedrock/amazon.titan-embed-text-v2:0",
+    input=["good morning from litellm"],
+    encoding_format="float"  # Returns float array
+)
+
+# Binary format
+response = embedding(
+    model="bedrock/amazon.titan-embed-text-v2:0",
+    input=["good morning from litellm"],
+    encoding_format="base64"  # Returns base64 encoded binary
+)
+```
+
+## Supported AWS Bedrock Embedding Models
+
+| Model Name           | Usage                               | Supported Additional OpenAI params |
+|----------------------|---------------------------------------------|-----|
+| Titan Embeddings V2 | `embedding(model="bedrock/amazon.titan-embed-text-v2:0", input=input)` | `dimensions`, `encoding_format` |
+| Titan Embeddings - V1 | `embedding(model="bedrock/amazon.titan-embed-text-v1", input=input)` | [here](https://github.com/BerriAI/litellm/blob/f5905e100068e7a4d61441d7453d7cf5609c2121/litellm/llms/bedrock/embed/amazon_titan_g1_transformation.py#L53)
+| Titan Multimodal Embeddings | `embedding(model="bedrock/amazon.titan-embed-image-v1", input=input)` | [here](https://github.com/BerriAI/litellm/blob/f5905e100068e7a4d61441d7453d7cf5609c2121/litellm/llms/bedrock/embed/amazon_titan_multimodal_transformation.py#L28) |
+| Cohere Embeddings - English | `embedding(model="bedrock/cohere.embed-english-v3", input=input)` | [here](https://github.com/BerriAI/litellm/blob/f5905e100068e7a4d61441d7453d7cf5609c2121/litellm/llms/bedrock/embed/cohere_transformation.py#L18)
+| Cohere Embeddings - Multilingual | `embedding(model="bedrock/cohere.embed-multilingual-v3", input=input)` | [here](https://github.com/BerriAI/litellm/blob/f5905e100068e7a4d61441d7453d7cf5609c2121/litellm/llms/bedrock/embed/cohere_transformation.py#L18)
+
+### Advanced - [Drop Unsupported Params](https://docs.litellm.ai/docs/completion/drop_params#openai-proxy-usage)
+
+### Advanced - [Pass model/provider-specific Params](https://docs.litellm.ai/docs/completion/provider_specific_params#proxy-usage)
+
 ## Image Generation
 Use this for stable diffusion, and amazon nova canvas on bedrock
 

litellm/integrations/langsmith.py

@@ -39,6 +39,7 @@ def __init__(
         langsmith_api_key: Optional[str] = None,
         langsmith_project: Optional[str] = None,
         langsmith_base_url: Optional[str] = None,
+        langsmith_sampling_rate: Optional[float] = None,
         **kwargs,
     ):
         self.flush_lock = asyncio.Lock()
@@ -49,7 +50,8 @@ def __init__(
             langsmith_base_url=langsmith_base_url,
         )
         self.sampling_rate: float = (
-            float(os.getenv("LANGSMITH_SAMPLING_RATE"))  # type: ignore
+            langsmith_sampling_rate
+            or float(os.getenv("LANGSMITH_SAMPLING_RATE"))  # type: ignore
             if os.getenv("LANGSMITH_SAMPLING_RATE") is not None
             and os.getenv("LANGSMITH_SAMPLING_RATE").strip().isdigit()  # type: ignore
             else 1.0
@@ -76,26 +78,14 @@ def get_credentials_from_env(
         langsmith_base_url: Optional[str] = None,
     ) -> LangsmithCredentialsObject:
         _credentials_api_key = langsmith_api_key or os.getenv("LANGSMITH_API_KEY")
-        if _credentials_api_key is None:
-            raise Exception(
-                "Invalid Langsmith API Key given. _credentials_api_key=None."
-            )
         _credentials_project = (
             langsmith_project or os.getenv("LANGSMITH_PROJECT") or "litellm-completion"
         )
-        if _credentials_project is None:
-            raise Exception(
-                "Invalid Langsmith API Key given. _credentials_project=None."
-            )
         _credentials_base_url = (
             langsmith_base_url
             or os.getenv("LANGSMITH_BASE_URL")
             or "https://api.smith.langchain.com"
         )
-        if _credentials_base_url is None:
-            raise Exception(
-                "Invalid Langsmith API Key given. _credentials_base_url=None."
-            )
 
         return LangsmithCredentialsObject(
             LANGSMITH_API_KEY=_credentials_api_key,
@@ -200,12 +190,7 @@ def _prepare_log_data(
 
     def log_success_event(self, kwargs, response_obj, start_time, end_time):
         try:
-            sampling_rate = (
-                float(os.getenv("LANGSMITH_SAMPLING_RATE"))  # type: ignore
-                if os.getenv("LANGSMITH_SAMPLING_RATE") is not None
-                and os.getenv("LANGSMITH_SAMPLING_RATE").strip().isdigit()  # type: ignore
-                else 1.0
-            )
+            sampling_rate = self._get_sampling_rate_to_use_for_request(kwargs=kwargs)
             random_sample = random.random()
             if random_sample > sampling_rate:
                 verbose_logger.info(
@@ -219,6 +204,7 @@ def log_success_event(self, kwargs, response_obj, start_time, end_time):
                 kwargs,
                 response_obj,
             )
+
             credentials = self._get_credentials_to_use_for_request(kwargs=kwargs)
             data = self._prepare_log_data(
                 kwargs=kwargs,
@@ -245,7 +231,7 @@ def log_success_event(self, kwargs, response_obj, start_time, end_time):
 
     async def async_log_success_event(self, kwargs, response_obj, start_time, end_time):
         try:
-            sampling_rate = self.sampling_rate
+            sampling_rate = self._get_sampling_rate_to_use_for_request(kwargs=kwargs)
             random_sample = random.random()
             if random_sample > sampling_rate:
                 verbose_logger.info(
@@ -286,7 +272,7 @@ async def async_log_success_event(self, kwargs, response_obj, start_time, end_ti
             )
 
     async def async_log_failure_event(self, kwargs, response_obj, start_time, end_time):
-        sampling_rate = self.sampling_rate
+        sampling_rate = self._get_sampling_rate_to_use_for_request(kwargs=kwargs)
         random_sample = random.random()
         if random_sample > sampling_rate:
             verbose_logger.info(
@@ -417,6 +403,17 @@ def _group_batches_by_credentials(self) -> Dict[CredentialsKey, BatchGroup]:
 
         for queue_object in self.log_queue:
             credentials = queue_object["credentials"]
+            # if credential missing, skip - log warning
+            if (
+                credentials["LANGSMITH_API_KEY"] is None
+                or credentials["LANGSMITH_PROJECT"] is None
+            ):
+                verbose_logger.warning(
+                    "Langsmith Logging - credentials missing - api_key: %s, project: %s",
+                    credentials["LANGSMITH_API_KEY"],
+                    credentials["LANGSMITH_PROJECT"],
+                )
+                continue
             key = CredentialsKey(
                 api_key=credentials["LANGSMITH_API_KEY"],
                 project=credentials["LANGSMITH_PROJECT"],
@@ -432,6 +429,19 @@ def _group_batches_by_credentials(self) -> Dict[CredentialsKey, BatchGroup]:
 
         return log_queue_by_credentials
 
+    def _get_sampling_rate_to_use_for_request(self, kwargs: Dict[str, Any]) -> float:
+        standard_callback_dynamic_params: Optional[StandardCallbackDynamicParams] = (
+            kwargs.get("standard_callback_dynamic_params", None)
+        )
+        sampling_rate: float = self.sampling_rate
+        if standard_callback_dynamic_params is not None:
+            _sampling_rate = standard_callback_dynamic_params.get(
+                "langsmith_sampling_rate"
+            )
+            if _sampling_rate is not None:
+                sampling_rate = float(_sampling_rate)
+        return sampling_rate
+
     def _get_credentials_to_use_for_request(
         self, kwargs: Dict[str, Any]
     ) -> LangsmithCredentialsObject:
@@ -442,9 +452,9 @@ def _get_credentials_to_use_for_request(
 
         Otherwise, use the default credentials.
         """
-        standard_callback_dynamic_params: Optional[
-            StandardCallbackDynamicParams
-        ] = kwargs.get("standard_callback_dynamic_params", None)
+        standard_callback_dynamic_params: Optional[StandardCallbackDynamicParams] = (
+            kwargs.get("standard_callback_dynamic_params", None)
+        )
         if standard_callback_dynamic_params is not None:
             credentials = self.get_credentials_from_env(
                 langsmith_api_key=standard_callback_dynamic_params.get(