`max_tokens` param not work in ChatPerplexity model

[YJU-KimJeongSu]

Checked other resources

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

Example Code

chat_prompt = ...

model = ChatPerplexity(
    pplx_api_key=PERPLEXITY_API_KEY,
    model="llama-3.1-sonar-small-128k-online",
    temperature=0.1,
    max_tokens=200,
)

chain = chat_prompt | model

response = chain.invoke(...)

Error Message and Stack Trace (if applicable)

No response

Description

Perplexity Docs Example :

import requests

url = "https://api.perplexity.ai/chat/completions"

payload = {
    "max_tokens": 100,
    "model": "llama-3.1-sonar-small-128k-online",
    "messages": [
        {
            "content": "read me a long fairy tale",
            "role": "user"
        }
    ]
}
headers = {
    "Authorization": ...,
    "Content-Type": "application/json"
}

---

Langchain’s Current Implementation :

https://github.com/langchain-ai/langchain/blob/16918842bf86de1b493229310b0f6fc593d7a686/libs/community/langchain_community/chat_models/perplexity.py#L147-L156

https://github.com/langchain-ai/langchain/blob/16918842bf86de1b493229310b0f6fc593d7a686/libs/community/langchain_community/chat_models/perplexity.py#L267-L275

---

Suggestion :

 @property 
 def _default_params(self) -> Dict[str, Any]: 
     """Get the default parameters for calling PerplexityChat API.""" 
     return { 
         "request_timeout": self.request_timeout, 
         "stream": self.streaming, 
         "temperature": self.temperature, 
         **self.model_kwargs, 
     } 

 @property 
 def _invocation_params(self) -> Mapping[str, Any]: 
     """Get the parameters used to invoke the model.""" 
     pplx_creds: Dict[str, Any] = { 
         "api_key": self.pplx_api_key, 
         "api_base": "https://api.perplexity.ai", 
         "model": self.model, 
         "max_tokens": self.max_tokens,
     } 
     return {**pplx_creds, **self._default_params} 

System Info

System Information

OS: Darwin OS Version: Darwin Kernel Version 24.1.0: Thu Oct 10 22:08:48 PDT 2024; root:xnu-11215.41.3~5/RELEASE_ARM64_T6000 Python Version: 3.10.14 (main, Mar 19 2024, 21:46:16) [Clang 15.0.0 (clang-1500.3.9.4)]

Package Information

langchain_core: 0.3.17 langchain: 0.2.15 langchain_community: 0.2.14 langsmith: 0.1.128 langchain_anthropic: 0.3.0 langchain_experimental: 0.0.57 langchain_google_genai: 2.0.4 langchain_google_vertexai: 1.0.4 langchain_mongodb: 0.2.0 langchain_openai: 0.0.5 langchain_text_splitters: 0.2.2

Optional packages not installed

langgraph langserve

Other Dependencies

aiohttp: 3.9.3 anthropic: 0.39.0 anthropic[vertexai]: Installed. No version info available. async-timeout: 4.0.3 dataclasses-json: 0.6.7 defusedxml: 0.7.1 faker: Installed. No version info available. google-cloud-aiplatform: 1.51.0 google-cloud-storage: 2.16.0 google-generativeai: 0.8.3 httpx: 0.27.2 jinja2: 3.1.2 jsonpatch: 1.33 numpy: 1.23.1 openai: 1.10.0 orjson: 3.10.2 packaging: 23.2 pandas: 2.2.0 pillow: 10.1.0 presidio-analyzer: Installed. No version info available. presidio-anonymizer: Installed. No version info available. pydantic: 2.9.2 pymongo: 4.8.0 PyYAML: 6.0.1 requests: 2.31.0 sentence-transformers: Installed. No version info available. SQLAlchemy: 2.0.25 tabulate: 0.9.0 tenacity: 8.2.3 tiktoken: 0.5.2 typing-extensions: 4.9.0 vowpal-wabbit-next: Installed. No version info available.