ChatPerplexity: 'str' object has no attribute 'choices'

[n-sviridenko]

Checked other resources

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

Example Code

from langchain_community.chat_models import ChatPerplexity
research_model = ChatPerplexity(
        model="llama-3.1-sonar-large-128k-online",
        temperature=0,
        # to not emit messages to the client
        disable_streaming=True,
    )

research_prompt = 'How many starts are there?'
research_response = research_model.invoke([HumanMessage(content=research_prompt)])

Error Message and Stack Trace (if applicable)

AttributeError("'str' object has no attribute 'choices'")Traceback (most recent call last):

File "/Users/nsviridenko/.local/share/virtualenvs/nce-agent-dIPyehe6/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 633, in generate
self._generate_with_cache(

File "/Users/nsviridenko/.local/share/virtualenvs/nce-agent-dIPyehe6/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 851, in _generate_with_cache
result = self._generate(
^^^^^^^^^^^^^^^

File "/Users/nsviridenko/.local/share/virtualenvs/nce-agent-dIPyehe6/lib/python3.11/site-packages/langchain_community/chat_models/perplexity.py", line 265, in _generate
content=response.choices[0].message.content,
^^^^^^^^^^^^^^^^

AttributeError: 'str' object has no attribute 'choices'

Description

When trying to use ChatPerplexity, it throws an error.

System Info

System Information

OS: Darwin
OS Version: Darwin Kernel Version 20.6.0: Tue Jun 21 20:50:28 PDT 2022; root:xnu-7195.141.32~1/RELEASE_X86_64
Python Version: 3.11.5 (main, Sep 29 2024, 15:09:05) [Clang 12.0.5 (clang-1205.0.22.11)]

Package Information

langchain_core: 0.3.21
langchain: 0.3.9
langchain_community: 0.3.9
langsmith: 0.1.147
langchain_anthropic: 0.3.0
langchain_openai: 0.2.10
langchain_text_splitters: 0.3.2
langgraph_api: 0.0.15
langgraph_cli: 0.1.65
langgraph_license: Installed. No version info available.
langgraph_sdk: 0.1.48
langgraph_storage: Installed. No version info available.

Optional packages not installed

langserve

Other Dependencies

aiohttp: 3.11.11
anthropic: 0.42.0
async-timeout: Installed. No version info available.
click: 8.1.8
cryptography: 43.0.3
dataclasses-json: 0.6.7
defusedxml: 0.7.1
httpx: 0.28.1
httpx-sse: 0.4.0
jsonpatch: 1.33
jsonschema-rs: 0.25.1
langgraph: 0.2.56
langgraph-checkpoint: 2.0.9
langsmith-pyo3: Installed. No version info available.
numpy: 1.26.4
openai: 1.55.3
orjson: 3.10.13
packaging: 24.2
pydantic: 2.10.4
pydantic-settings: 2.7.1
pyjwt: 2.10.1
python-dotenv: 1.0.1
PyYAML: 6.0.2
requests: 2.32.3
requests-toolbelt: 1.0.0
SQLAlchemy: 2.0.27
sse-starlette: 2.1.3
starlette: 0.45.2
structlog: 24.4.0
tenacity: 8.5.0
tiktoken: 0.8.0
typing-extensions: 4.12.2
uvicorn: 0.34.0
watchfiles: 1.0.3

[keenborder786]

@n-sviridenko Can you use the following class:

"""Wrapper around Perplexity APIs."""
from langchain_community.chat_models import ChatPerplexity 

class CustomChatPerplexity(ChatPerplexity):
    
    def _generate(
        self,
        messages: List[BaseMessage],
        stop: Optional[List[str]] = None,
        run_manager: Optional[CallbackManagerForLLMRun] = None,
        **kwargs: Any,
    ) -> ChatResult:
        if self.streaming:
            stream_iter = self._stream(
                messages, stop=stop, run_manager=run_manager, **kwargs
            )
            if stream_iter:
                return generate_from_stream(stream_iter)
        message_dicts, params = self._create_message_dicts(messages, stop)
        params = {**params, **kwargs}
        response = self.client.chat.completions.create(messages=message_dicts, **params)
        print(response) # Outputing the response to see what is being returned
        message = AIMessage(
            content=response.choices[0].message.content,
            additional_kwargs={"citations": response.citations},
        )
        return ChatResult(generations=[ChatGeneration(message=message)])

Because according to official Preplexity documentation: https://docs.perplexity.ai/api-reference/chat-completions. The response should be a json. Therefore I wanna see the output of the response that you are getting, before I can help you.