Fix BadRequestError while using OpenAI O1 series models | Add option to bypass temperature (#2151)

we were about to use OpenAI's O1 model for FactualCorrectness metric
since it is good at reasoning, but faced BadRequestError on ragas
eventhough it worked fine in langchain and llama index, then I came to
know ragas is calculating temperature, but it is not supported in O1
models, so added a way to bypass temperature

Reproducible code
```python
from langchain_openai import ChatOpenAI
from llama_index.llms.openai import OpenAI
from ragas.llms import LlamaIndexLLMWrapper,LangchainLLMWrapper
from langchain_core.prompt_values import StringPromptValue

api_key = "<your_api_key>"

langchain_llm=ChatOpenAI(model="o1", api_key=api_key)
llama_index_llm=OpenAI(model="o1", api_key=api_key)

# Both Will work fine
print(langchain_llm.invoke("hi"))
print(llama_index_llm.complete("hi"))

prompt = StringPromptValue(text="hi")

# Both Will raise error
await LlamaIndexLLMWrapper(llama_index_llm).agenerate_text(prompt)
await LangchainLLMWrapper(langchain_llm).agenerate_text(prompt)

```
Error
```
BadRequestError: Error code: 400 - {'error': {'message': "Unsupported parameter: 'temperature' is not supported with this model.", 'type': 'invalid_request_error', 'param': 'temperature', 'code': 'unsupported_parameter'}}
```

After Fix
```python
# Both Will work as expected
await LlamaIndexLLMWrapper(llama_index_llm,bypass_temperature=True).agenerate_text(prompt)
await LangchainLLMWrapper(langchain_llm,bypass_temperature=True).agenerate_text(prompt)
```

Due to scalability reasons, I am adding a flag instead of checking the
model name and removing the temperature

Co-authored-by: Vignesh Arivazhagan <vignesh.arivazhagan@solitontech.com>

Author: vignesh14052002

src/ragas/llms/base.py

@@ -142,13 +142,16 @@ def __init__(
         run_config: t.Optional[RunConfig] = None,
         is_finished_parser: t.Optional[t.Callable[[LLMResult], bool]] = None,
         cache: t.Optional[CacheInterface] = None,
+        bypass_temperature: bool = False,
     ):
         super().__init__(cache=cache)
         self.langchain_llm = langchain_llm
         if run_config is None:
             run_config = RunConfig()
         self.set_run_config(run_config)
         self.is_finished_parser = is_finished_parser
+        # Certain LLMs (e.g., OpenAI o1 series) do not support temperature
+        self.bypass_temperature = bypass_temperature
 
     def is_finished(self, response: LLMResult) -> bool:
         """
@@ -252,7 +255,7 @@ async def agenerate_text(
         old_temperature: float | None = None
         if temperature is None:
             temperature = self.get_temperature(n=n)
-        if hasattr(self.langchain_llm, "temperature"):
+        if hasattr(self.langchain_llm, "temperature") and not self.bypass_temperature:
             self.langchain_llm.temperature = temperature  # type: ignore
             old_temperature = temperature
 
@@ -311,9 +314,12 @@ def __init__(
         llm: BaseLLM,
         run_config: t.Optional[RunConfig] = None,
         cache: t.Optional[CacheInterface] = None,
+        bypass_temperature: bool = False,
     ):
         super().__init__(cache=cache)
         self.llm = llm
+        # Certain LLMs (e.g., OpenAI o1 series) do not support temperature
+        self.bypass_temperature = bypass_temperature
 
         try:
             self._signature = type(self.llm).__name__.lower()
@@ -378,6 +384,10 @@ async def agenerate_text(
             temperature = self.get_temperature(n)
 
         kwargs = self.check_args(n, temperature, stop, callbacks)
+
+        if self.bypass_temperature:
+            kwargs.pop("temperature", None)
+
         li_response = await self.llm.acomplete(prompt.to_string(), **kwargs)
 
         return LLMResult(generations=[[Generation(text=li_response.text)]])