style(test_completion.py): fix merge conflict

litellm/llms/nlp_cloud.py

@@ -1,9 +1,10 @@
-import os
+import os, types
 import json
 from enum import Enum
 import requests
 import time
-from typing import Callable
+from typing import Callable, Optional
+import litellm
 from litellm.utils import ModelResponse
 
 class NLPCloudError(Exception):
@@ -14,6 +15,75 @@ class NLPCloudError(Exception):
             self.message
         )  # Call the base class constructor with the parameters it needs
 
+class NLPCloudConfig():
+    """
+    Reference: https://docs.nlpcloud.com/#generation
+
+    - `max_length` (int): Optional. The maximum number of tokens that the generated text should contain.
+
+    - `length_no_input` (boolean): Optional. Whether `min_length` and `max_length` should not include the length of the input text.
+
+    - `end_sequence` (string): Optional. A specific token that should be the end of the generated sequence.
+
+    - `remove_end_sequence` (boolean): Optional. Whether to remove the `end_sequence` string from the result.
+
+    - `remove_input` (boolean): Optional. Whether to remove the input text from the result.
+
+    - `bad_words` (list of strings): Optional. List of tokens that are not allowed to be generated.
+
+    - `temperature` (float): Optional. Temperature sampling. It modulates the next token probabilities.
+
+    - `top_p` (float): Optional. Top P sampling. Below 1, only the most probable tokens with probabilities that add up to top_p or higher are kept for generation.
+
+    - `top_k` (int): Optional. Top K sampling. The number of highest probability vocabulary tokens to keep for top k filtering.
+
+    - `repetition_penalty` (float): Optional. Prevents the same word from being repeated too many times.
+
+    - `num_beams` (int): Optional. Number of beams for beam search.
+
+    - `num_return_sequences` (int): Optional. The number of independently computed returned sequences.
+    """
+    max_length: Optional[int]=None
+    length_no_input: Optional[bool]=None
+    end_sequence: Optional[str]=None
+    remove_end_sequence: Optional[bool]=None
+    remove_input: Optional[bool]=None
+    bad_words: Optional[list]=None
+    temperature: Optional[float]=None
+    top_p: Optional[float]=None
+    top_k: Optional[int]=None
+    repetition_penalty: Optional[float]=None
+    num_beams: Optional[int]=None
+    num_return_sequences: Optional[int]=None
+
+
+    def __init__(self,
+                 max_length: Optional[int]=None,
+                 length_no_input: Optional[bool]=None,
+                 end_sequence: Optional[str]=None,
+                 remove_end_sequence: Optional[bool]=None,
+                 remove_input: Optional[bool]=None,
+                 bad_words: Optional[list]=None,
+                 temperature: Optional[float]=None,
+                 top_p: Optional[float]=None,
+                 top_k: Optional[int]=None,
+                 repetition_penalty: Optional[float]=None,
+                 num_beams: Optional[int]=None,
+                 num_return_sequences: Optional[int]=None) -> None:
+        
+        locals_ = locals()
+        for key, value in locals_.items():
+            if key != 'self' and value is not None:
+                setattr(self.__class__, key, value)
+    
+    @classmethod
+    def get_config(cls):
+        return {k: v for k, v in cls.__dict__.items() 
+                if not k.startswith('__') 
+                and not isinstance(v, (types.FunctionType, types.BuiltinFunctionType, classmethod, staticmethod)) 
+                and v is not None}
+
+
 def validate_environment(api_key):
     headers = {
         "accept": "application/json",
@@ -37,6 +107,13 @@ def completion(
     default_max_tokens_to_sample=None,
 ):
     headers = validate_environment(api_key)
+
+    ## Load Config
+    config = litellm.NLPCloudConfig.get_config() 
+    for k, v in config.items(): 
+        if k not in optional_params: # completion(top_k=3) > togetherai_config(top_k=3) <- allows for dynamic variables to be passed in
+            optional_params[k] = v
+
     completion_url_fragment_1 = "https://api.nlpcloud.io/v1/gpu/"
     completion_url_fragment_2 = "/generation"
     model = model