openai[patch]: update openai params (#23691)

**Description:** Explicitly add parameters from openai API



- [X] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

---------

Co-authored-by: Erick Friis <erick@langchain.dev>

libs/partners/openai/langchain_openai/chat_models/base.py

@@ -319,10 +319,26 @@ class BaseChatOpenAI(BaseChatModel):
         None."""
     max_retries: int = 2
     """Maximum number of retries to make when generating."""
+    presence_penalty: Optional[float] = None
+    """Penalizes repeated tokens."""
+    frequency_penalty: Optional[float] = None
+    """Penalizes repeated tokens according to frequency."""
+    seed: Optional[int] = None
+    """Seed for generation"""
+    logprobs: Optional[bool] = False
+    """Whether to return logprobs."""
+    top_logprobs: Optional[int] = None
+    """Number of most likely tokens to return at each token position, each with
+     an associated log probability. `logprobs` must be set to true 
+     if this parameter is used."""
+    logit_bias: Optional[Dict[int, int]] = None
+    """Modify the likelihood of specified tokens appearing in the completion."""
     streaming: bool = False
     """Whether to stream the results or not."""
     n: int = 1
     """Number of chat completions to generate for each prompt."""
+    top_p: Optional[float] = None
+    """Total probability mass of tokens to consider at each step."""
     max_tokens: Optional[int] = None
     """Maximum number of tokens to generate."""
     tiktoken_model_name: Optional[str] = None
@@ -444,6 +460,13 @@ class BaseChatOpenAI(BaseChatModel):
             "stream": self.streaming,
             "n": self.n,
             "temperature": self.temperature,
+            "presence_penalty": self.presence_penalty,
+            "frequency_penalty": self.frequency_penalty,
+            "seed": self.seed,
+            "top_p": self.top_p,
+            "logprobs": self.logprobs,
+            "top_logprobs": self.top_logprobs,
+            "logit_bias": self.logit_bias,
             **self.model_kwargs,
         }
         if self.max_tokens is not None: