langchain: InvalidRequestError: Unrecognized request arguments supplied: function_call, functions
Issue with current documentation:
I am following the instruction from this doc: DOC: Structure answers with OpenAI functions
But this gives some error.
Code
from langchain.chains import RetrievalQA
from langchain.document_loaders import TextLoader
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import Chroma
from langchain.chat_models import AzureChatOpenAI
from langchain.chat_models import ChatOpenAI
from langchain.chains.combine_documents.stuff import StuffDocumentsChain
from langchain.prompts import PromptTemplate
from langchain.chains import create_qa_with_sources_chain
path_txt = r"C:\Users\a126291\OneDrive - AmerisourceBergen(ABC)\data\langchain\state_of_the_union.txt"
def get_config_dict():
import os
import yaml
with open(os.path.expanduser('~/.config/config.yaml')) as fh:
config = yaml.safe_load(fh)
# openai
keys = ["OPENAI_API_KEY","OPENAI_API_TYPE","OPENAI_API_BASE","OPENAI_API_VERSION"]
for key in keys:
os.environ[key] = config.get(key)
return config
config = get_config_dict()
#========= qa chain
loader = TextLoader(path_txt, encoding="utf-8")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_documents(documents)
for i, text in enumerate(texts):
text.metadata["source"] = f"{i}-pl"
embeddings = OpenAIEmbeddings(model="text-embedding-ada-002", chunk_size=1)
docsearch = Chroma.from_documents(texts, embeddings)
# vectorstore = Chroma.from_documents(texts, embeddings)
# retriever = vectorstore.as_retriever()
llm = AzureChatOpenAI(**config['kw_azure_llm'],temperature=0.4)
#------- query
qa_chain = create_qa_with_sources_chain(llm)
doc_prompt = PromptTemplate(
template="Content: {page_content}\nSource: {source}",
input_variables=["page_content", "source"],
)
final_qa_chain = StuffDocumentsChain(
llm_chain=qa_chain,
document_variable_name="context",
document_prompt=doc_prompt,
)
retrieval_qa = RetrievalQA(
retriever=docsearch.as_retriever(), combine_documents_chain=final_qa_chain
)
query = "What did the president say about russia"
retrieval_qa.run(query)
Error: InvalidRequestError: Unrecognized request arguments supplied: function_call, functions
---------------------------------------------------------------------------
InvalidRequestError Traceback (most recent call last)
Cell In[36], line 69
64 retrieval_qa = RetrievalQA(
65 retriever=docsearch.as_retriever(), combine_documents_chain=final_qa_chain
66 )
68 query = "What did the president say about russia"
---> 69 retrieval_qa.run(query)
File ~\venv\py311openai\Lib\site-packages\langchain\chains\base.py:290, in Chain.run(self, callbacks, tags, *args, **kwargs)
288 if len(args) != 1:
289 raise ValueError("`run` supports only one positional argument.")
--> 290 return self(args[0], callbacks=callbacks, tags=tags)[_output_key]
292 if kwargs and not args:
293 return self(kwargs, callbacks=callbacks, tags=tags)[_output_key]
File ~\venv\py311openai\Lib\site-packages\langchain\chains\base.py:166, in Chain.__call__(self, inputs, return_only_outputs, callbacks, tags, include_run_info)
164 except (KeyboardInterrupt, Exception) as e:
165 run_manager.on_chain_error(e)
--> 166 raise e
167 run_manager.on_chain_end(outputs)
168 final_outputs: Dict[str, Any] = self.prep_outputs(
169 inputs, outputs, return_only_outputs
170 )
File ~\venv\py311openai\Lib\site-packages\langchain\chains\base.py:160, in Chain.__call__(self, inputs, return_only_outputs, callbacks, tags, include_run_info)
154 run_manager = callback_manager.on_chain_start(
155 dumpd(self),
156 inputs,
157 )
158 try:
159 outputs = (
--> 160 self._call(inputs, run_manager=run_manager)
161 if new_arg_supported
162 else self._call(inputs)
163 )
164 except (KeyboardInterrupt, Exception) as e:
165 run_manager.on_chain_error(e)
File ~\venv\py311openai\Lib\site-packages\langchain\chains\retrieval_qa\base.py:120, in BaseRetrievalQA._call(self, inputs, run_manager)
117 question = inputs[self.input_key]
119 docs = self._get_docs(question)
--> 120 answer = self.combine_documents_chain.run(
121 input_documents=docs, question=question, callbacks=_run_manager.get_child()
122 )
124 if self.return_source_documents:
125 return {self.output_key: answer, "source_documents": docs}
File ~\venv\py311openai\Lib\site-packages\langchain\chains\base.py:293, in Chain.run(self, callbacks, tags, *args, **kwargs)
290 return self(args[0], callbacks=callbacks, tags=tags)[_output_key]
292 if kwargs and not args:
--> 293 return self(kwargs, callbacks=callbacks, tags=tags)[_output_key]
295 if not kwargs and not args:
296 raise ValueError(
297 "`run` supported with either positional arguments or keyword arguments,"
298 " but none were provided."
299 )
File ~\venv\py311openai\Lib\site-packages\langchain\chains\base.py:166, in Chain.__call__(self, inputs, return_only_outputs, callbacks, tags, include_run_info)
164 except (KeyboardInterrupt, Exception) as e:
165 run_manager.on_chain_error(e)
--> 166 raise e
167 run_manager.on_chain_end(outputs)
168 final_outputs: Dict[str, Any] = self.prep_outputs(
169 inputs, outputs, return_only_outputs
170 )
File ~\venv\py311openai\Lib\site-packages\langchain\chains\base.py:160, in Chain.__call__(self, inputs, return_only_outputs, callbacks, tags, include_run_info)
154 run_manager = callback_manager.on_chain_start(
155 dumpd(self),
156 inputs,
157 )
158 try:
159 outputs = (
--> 160 self._call(inputs, run_manager=run_manager)
161 if new_arg_supported
162 else self._call(inputs)
163 )
164 except (KeyboardInterrupt, Exception) as e:
165 run_manager.on_chain_error(e)
File ~\venv\py311openai\Lib\site-packages\langchain\chains\combine_documents\base.py:84, in BaseCombineDocumentsChain._call(self, inputs, run_manager)
82 # Other keys are assumed to be needed for LLM prediction
83 other_keys = {k: v for k, v in inputs.items() if k != self.input_key}
---> 84 output, extra_return_dict = self.combine_docs(
85 docs, callbacks=_run_manager.get_child(), **other_keys
86 )
87 extra_return_dict[self.output_key] = output
88 return extra_return_dict
File ~\venv\py311openai\Lib\site-packages\langchain\chains\combine_documents\stuff.py:87, in StuffDocumentsChain.combine_docs(self, docs, callbacks, **kwargs)
85 inputs = self._get_inputs(docs, **kwargs)
86 # Call predict on the LLM.
---> 87 return self.llm_chain.predict(callbacks=callbacks, **inputs), {}
File ~\venv\py311openai\Lib\site-packages\langchain\chains\llm.py:252, in LLMChain.predict(self, callbacks, **kwargs)
237 def predict(self, callbacks: Callbacks = None, **kwargs: Any) -> str:
238 """Format prompt with kwargs and pass to LLM.
239
240 Args:
(...)
250 completion = llm.predict(adjective="funny")
251 """
--> 252 return self(kwargs, callbacks=callbacks)[self.output_key]
File ~\venv\py311openai\Lib\site-packages\langchain\chains\base.py:166, in Chain.__call__(self, inputs, return_only_outputs, callbacks, tags, include_run_info)
164 except (KeyboardInterrupt, Exception) as e:
165 run_manager.on_chain_error(e)
--> 166 raise e
167 run_manager.on_chain_end(outputs)
168 final_outputs: Dict[str, Any] = self.prep_outputs(
169 inputs, outputs, return_only_outputs
170 )
File ~\venv\py311openai\Lib\site-packages\langchain\chains\base.py:160, in Chain.__call__(self, inputs, return_only_outputs, callbacks, tags, include_run_info)
154 run_manager = callback_manager.on_chain_start(
155 dumpd(self),
156 inputs,
157 )
158 try:
159 outputs = (
--> 160 self._call(inputs, run_manager=run_manager)
161 if new_arg_supported
162 else self._call(inputs)
163 )
164 except (KeyboardInterrupt, Exception) as e:
165 run_manager.on_chain_error(e)
File ~\venv\py311openai\Lib\site-packages\langchain\chains\llm.py:92, in LLMChain._call(self, inputs, run_manager)
87 def _call(
88 self,
89 inputs: Dict[str, Any],
90 run_manager: Optional[CallbackManagerForChainRun] = None,
91 ) -> Dict[str, str]:
---> 92 response = self.generate([inputs], run_manager=run_manager)
93 return self.create_outputs(response)[0]
File ~\venv\py311openai\Lib\site-packages\langchain\chains\llm.py:102, in LLMChain.generate(self, input_list, run_manager)
100 """Generate LLM result from inputs."""
101 prompts, stop = self.prep_prompts(input_list, run_manager=run_manager)
--> 102 return self.llm.generate_prompt(
103 prompts,
104 stop,
105 callbacks=run_manager.get_child() if run_manager else None,
106 **self.llm_kwargs,
107 )
File ~\venv\py311openai\Lib\site-packages\langchain\chat_models\base.py:167, in BaseChatModel.generate_prompt(self, prompts, stop, callbacks, **kwargs)
159 def generate_prompt(
160 self,
161 prompts: List[PromptValue],
(...)
164 **kwargs: Any,
165 ) -> LLMResult:
166 prompt_messages = [p.to_messages() for p in prompts]
--> 167 return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)
File ~\venv\py311openai\Lib\site-packages\langchain\chat_models\base.py:102, in BaseChatModel.generate(self, messages, stop, callbacks, tags, **kwargs)
100 except (KeyboardInterrupt, Exception) as e:
101 run_manager.on_llm_error(e)
--> 102 raise e
103 llm_output = self._combine_llm_outputs([res.llm_output for res in results])
104 generations = [res.generations for res in results]
File ~\venv\py311openai\Lib\site-packages\langchain\chat_models\base.py:94, in BaseChatModel.generate(self, messages, stop, callbacks, tags, **kwargs)
90 new_arg_supported = inspect.signature(self._generate).parameters.get(
91 "run_manager"
92 )
93 try:
---> 94 results = [
95 self._generate(m, stop=stop, run_manager=run_manager, **kwargs)
96 if new_arg_supported
97 else self._generate(m, stop=stop)
98 for m in messages
99 ]
100 except (KeyboardInterrupt, Exception) as e:
101 run_manager.on_llm_error(e)
File ~\venv\py311openai\Lib\site-packages\langchain\chat_models\base.py:95, in <listcomp>(.0)
90 new_arg_supported = inspect.signature(self._generate).parameters.get(
91 "run_manager"
92 )
93 try:
94 results = [
---> 95 self._generate(m, stop=stop, run_manager=run_manager, **kwargs)
96 if new_arg_supported
97 else self._generate(m, stop=stop)
98 for m in messages
99 ]
100 except (KeyboardInterrupt, Exception) as e:
101 run_manager.on_llm_error(e)
File ~\venv\py311openai\Lib\site-packages\langchain\chat_models\openai.py:359, in ChatOpenAI._generate(self, messages, stop, run_manager, **kwargs)
351 message = _convert_dict_to_message(
352 {
353 "content": inner_completion,
(...)
356 }
357 )
358 return ChatResult(generations=[ChatGeneration(message=message)])
--> 359 response = self.completion_with_retry(messages=message_dicts, **params)
360 return self._create_chat_result(response)
File ~\venv\py311openai\Lib\site-packages\langchain\chat_models\openai.py:307, in ChatOpenAI.completion_with_retry(self, **kwargs)
303 @retry_decorator
304 def _completion_with_retry(**kwargs: Any) -> Any:
305 return self.client.create(**kwargs)
--> 307 return _completion_with_retry(**kwargs)
File ~\venv\py311openai\Lib\site-packages\tenacity\__init__.py:289, in BaseRetrying.wraps.<locals>.wrapped_f(*args, **kw)
287 @functools.wraps(f)
288 def wrapped_f(*args: t.Any, **kw: t.Any) -> t.Any:
--> 289 return self(f, *args, **kw)
File ~\venv\py311openai\Lib\site-packages\tenacity\__init__.py:379, in Retrying.__call__(self, fn, *args, **kwargs)
377 retry_state = RetryCallState(retry_object=self, fn=fn, args=args, kwargs=kwargs)
378 while True:
--> 379 do = self.iter(retry_state=retry_state)
380 if isinstance(do, DoAttempt):
381 try:
File ~\venv\py311openai\Lib\site-packages\tenacity\__init__.py:314, in BaseRetrying.iter(self, retry_state)
312 is_explicit_retry = fut.failed and isinstance(fut.exception(), TryAgain)
313 if not (is_explicit_retry or self.retry(retry_state)):
--> 314 return fut.result()
316 if self.after is not None:
317 self.after(retry_state)
File ~\AppData\Local\Programs\Python\Python311\Lib\concurrent\futures\_base.py:449, in Future.result(self, timeout)
447 raise CancelledError()
448 elif self._state == FINISHED:
--> 449 return self.__get_result()
451 self._condition.wait(timeout)
453 if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]:
File ~\AppData\Local\Programs\Python\Python311\Lib\concurrent\futures\_base.py:401, in Future.__get_result(self)
399 if self._exception:
400 try:
--> 401 raise self._exception
402 finally:
403 # Break a reference cycle with the exception in self._exception
404 self = None
File ~\venv\py311openai\Lib\site-packages\tenacity\__init__.py:382, in Retrying.__call__(self, fn, *args, **kwargs)
380 if isinstance(do, DoAttempt):
381 try:
--> 382 result = fn(*args, **kwargs)
383 except BaseException: # noqa: B902
384 retry_state.set_exception(sys.exc_info()) # type: ignore[arg-type]
File ~\venv\py311openai\Lib\site-packages\langchain\chat_models\openai.py:305, in ChatOpenAI.completion_with_retry.<locals>._completion_with_retry(**kwargs)
303 @retry_decorator
304 def _completion_with_retry(**kwargs: Any) -> Any:
--> 305 return self.client.create(**kwargs)
File ~\venv\py311openai\Lib\site-packages\openai\api_resources\chat_completion.py:25, in ChatCompletion.create(cls, *args, **kwargs)
23 while True:
24 try:
---> 25 return super().create(*args, **kwargs)
26 except TryAgain as e:
27 if timeout is not None and time.time() > start + timeout:
File ~\venv\py311openai\Lib\site-packages\openai\api_resources\abstract\engine_api_resource.py:153, in EngineAPIResource.create(cls, api_key, api_base, api_type, request_id, api_version, organization, **params)
127 @classmethod
128 def create(
129 cls,
(...)
136 **params,
137 ):
138 (
139 deployment_id,
140 engine,
(...)
150 api_key, api_base, api_type, api_version, organization, **params
151 )
--> 153 response, _, api_key = requestor.request(
154 "post",
155 url,
156 params=params,
157 headers=headers,
158 stream=stream,
159 request_id=request_id,
160 request_timeout=request_timeout,
161 )
163 if stream:
164 # must be an iterator
165 assert not isinstance(response, OpenAIResponse)
File ~\venv\py311openai\Lib\site-packages\openai\api_requestor.py:298, in APIRequestor.request(self, method, url, params, headers, files, stream, request_id, request_timeout)
277 def request(
278 self,
279 method,
(...)
286 request_timeout: Optional[Union[float, Tuple[float, float]]] = None,
287 ) -> Tuple[Union[OpenAIResponse, Iterator[OpenAIResponse]], bool, str]:
288 result = self.request_raw(
289 method.lower(),
290 url,
(...)
296 request_timeout=request_timeout,
297 )
--> 298 resp, got_stream = self._interpret_response(result, stream)
299 return resp, got_stream, self.api_key
File ~\venv\py311openai\Lib\site-packages\openai\api_requestor.py:700, in APIRequestor._interpret_response(self, result, stream)
692 return (
693 self._interpret_response_line(
694 line, result.status_code, result.headers, stream=True
695 )
696 for line in parse_stream(result.iter_lines())
697 ), True
698 else:
699 return (
--> 700 self._interpret_response_line(
701 result.content.decode("utf-8"),
702 result.status_code,
703 result.headers,
704 stream=False,
705 ),
706 False,
707 )
File ~\venv\py311openai\Lib\site-packages\openai\api_requestor.py:763, in APIRequestor._interpret_response_line(self, rbody, rcode, rheaders, stream)
761 stream_error = stream and "error" in resp.data
762 if stream_error or not 200 <= rcode < 300:
--> 763 raise self.handle_error_response(
764 rbody, rcode, resp.data, rheaders, stream_error=stream_error
765 )
766 return resp
InvalidRequestError: Unrecognized request arguments supplied: function_call, functions
Idea or request for content:
No response
About this issue
- Original URL
- State: open
- Created a year ago
- Reactions: 1
- Comments: 20
Answer generated by a 🤖
Answer
Hello,
The error message “InvalidRequestError: Unrecognized request arguments supplied: function_call, functions” suggests that the function
retrieval_qa.run()is being called with incorrect arguments. In your case, you are passing a dictionary to therun()function.However, based on the context shared from the test_retrieval_qa.py file and the new context from the base.py file, the
run()function expects a dictionary with a specific key-value pair, not just any dictionary. The key should be “query” and the value should be the question string. In the example provided in the context, therun()function is called with a dictionary:To fix the error, you should modify your function call to match this format. Here’s how you can do it:
Please ensure that the query is a string and it is passed as a value to the “query” key in the dictionary.
If you continue to experience issues, please provide more information about the version of LangChain you are using and any other relevant details about your environment.
Best, Dosu
Sources
This response is meant to be useful, save you time, and share context. It is not meant to be a precise solution, but rather a starting point for your own research.
Help me be more useful! Please leave a đź‘Ť if this is helpful and đź‘Ž if it is irrelevant.
Use API version “2023-07-01-preview” and the 0613 version of the model
It wasn’t a problem a while ago, but now the problem has reappeared. openai.error.InvalidRequestError: Unrecognized request argument supplied: functions
Answer generated by a 🤖
Answer
Based on the context provided, it seems like you’re encountering the error because you’re passing the query directly to the
runmethod. Therunmethod in theChainclass, whichBaseRetrievalQAextends from, expects a dictionary as its argument, where the key is theinput_keyof theBaseRetrievalQAinstance and the value is the query string. In theBaseRetrievalQAclass, theinput_keyis set to “query”.So, instead of calling
retrieval_qa.run(query), you should callretrieval_qa.run({"query": query}). Here is the corrected code:This should resolve the “InvalidRequestError” you are encountering. If you continue to face issues, please provide more details about your code and the steps you’re following so I can assist you better.
Sources
This response is meant to be useful, save you time, and share context. It is not meant to be a precise solution, but rather a starting point for your own research.
Help me be more useful! Please leave a đź‘Ť if this is helpful and đź‘Ž if it is irrelevant.
🤖
Based on the error message you’re encountering, it seems like you’re passing arguments that are not recognized by the function you’re calling. The error “InvalidRequestError: Unrecognized request arguments supplied: function_call, functions” suggests that
function_callandfunctionsare not recognized arguments.In the LangChain library, functions such as
similarity_search_with_score_by_vector,asimilarity_search_by_vector,_asearch_with_score_by_vector,amax_marginal_relevance_search,max_marginal_relevance_search_with_score_by_vectorand others accept a specific set of arguments. These includeembedding,k,filter,search_params,offset,score_threshold,consistency, and**kwargs. The**kwargsargument is used to pass any additional named arguments to theQdrantClient.search()function. However,function_callandfunctionsare not recognized by this function. You can check the source code here.As for the
RetrievalQA.run()method, it’s not explicitly defined in the provided context. However, it’s likely that this method is inherited from theChainbase class or another superclass not shown in the context. The context does show the_call()and_acall()methods, which are likely called by therun()method. These methods takeinputs(a dictionary where the key is theinput_keyand the value is the question to be answered) andrun_manager(an optional instance ofCallbackManagerForChainRunorAsyncCallbackManagerForChainRunfor the_call()and_acall()methods respectively). If not provided, a no-operation manager is used. You can check the source code here.To resolve your issue, ensure that you are only passing recognized arguments to the function. If
function_callandfunctionsare not necessary for your query, you should remove them. If they are necessary, you should check the documentation forQdrantClient.search()to see how to correctly pass these arguments.Sources
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.
Help me be more useful! Please leave a đź‘Ť if this is helpful and đź‘Ž if it is irrelevant.
If you want to continue the conversation, start your reply with @dosu-bot.
I am still have this same problem. Does anyone know how to fix this?
I updated the code to:
Still got the same error:
Has anyone got the solution for this issue yet? I’m having the same issue
Error:
Never mind - I resolved the issue by upgrading
langchainto the later versions. (Currently sitting atlangchain==0.0.309)