Generative Agents don't work with AzureChatOpenAI

[AdrianP-]

System Info

I tried to run this example: https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html

But when I set the LLM with AzureChatOpenAI doesn't work. The error is:

Traceback (most recent call last):
  File "/home/adrian-ubuntu/projects/generative-agents/langchain_generative_agent.py", line 79, in <module>
    print(tommie.get_summary())
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/langchain/experimental/generative_agents/generative_agent.py", line 215, in get_summary
    self.summary = self._compute_agent_summary()
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/langchain/experimental/generative_agents/generative_agent.py", line 201, in _compute_agent_summary
    self.chain(prompt)
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/langchain/chains/base.py", line 239, in run
    return self(kwargs, callbacks=callbacks)[self.output_keys[0]]
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/langchain/chains/base.py", line 140, in __call__
    raise e
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/langchain/chains/base.py", line 134, in __call__
    self._call(inputs, run_manager=run_manager)
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/langchain/chains/llm.py", line 69, in _call
    response = self.generate([inputs], run_manager=run_manager)
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/langchain/chains/llm.py", line 79, in generate
    return self.llm.generate_prompt(
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/langchain/chat_models/base.py", line 142, in generate_prompt
    return self.generate(prompt_messages, stop=stop, callbacks=callbacks)
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/langchain/chat_models/base.py", line 90, in generate
    raise e
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/langchain/chat_models/base.py", line 82, in generate
    results = [
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/langchain/chat_models/base.py", line 83, in <listcomp>
    self._generate(m, stop=stop, run_manager=run_manager)
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/langchain/chat_models/openai.py", line 293, in _generate
    response = self.completion_with_retry(messages=message_dicts, **params)
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/langchain/chat_models/openai.py", line 254, in completion_with_retry
    return _completion_with_retry(**kwargs)
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/tenacity/__init__.py", line 289, in wrapped_f
    return self(f, *args, **kw)
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/tenacity/__init__.py", line 379, in __call__
    do = self.iter(retry_state=retry_state)
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/tenacity/__init__.py", line 314, in iter
    return fut.result()
  File "/usr/lib/python3.10/concurrent/futures/_base.py", line 451, in result
    return self.__get_result()
  File "/usr/lib/python3.10/concurrent/futures/_base.py", line 403, in __get_result
    raise self._exception
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/tenacity/__init__.py", line 382, in __call__
    result = fn(*args, **kwargs)
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/langchain/chat_models/openai.py", line 252, in _completion_with_retry
    return self.client.create(**kwargs)
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/openai/api_resources/chat_completion.py", line 25, in create
    return super().create(*args, **kwargs)
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 153, in create
    response, _, api_key = requestor.request(
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/openai/api_requestor.py", line 226, in request
    resp, got_stream = self._interpret_response(result, stream)
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/openai/api_requestor.py", line 620, in _interpret_response
    self._interpret_response_line(
  File "/home/adrian-ubuntu/projects/.venv_generative-agents/lib/python3.10/site-packages/openai/api_requestor.py", line 683, in _interpret_response_line
    raise self.handle_error_response(
openai.error.InvalidRequestError: Resource not found

Process finished with exit code 1

But with a simple example like:

model = AzureChatOpenAI(deployment_name="gpt-35-turbo", max_tokens=1500)
print(model([HumanMessage(content="Translate this sentence from English to French. I love programming.")]))

works perfectly (and both runs are configured with same env variables)

Version of langchain: 0.0.168

Who can help?

No response

Information

• [X] The official example notebooks/scripts
• [ ] My own modified scripts

Related Components

• [X] LLMs/Chat Models
• [ ] Embedding Models
• [ ] Prompts / Prompt Templates / Prompt Selectors
• [ ] Output Parsers
• [ ] Document Loaders
• [ ] Vector Stores / Retrievers
• [ ] Memory
• [ ] Agents / Agent Executors
• [ ] Tools / Toolkits
• [ ] Chains
• [ ] Callbacks/Tracing
• [ ] Async

Reproduction

import logging

from langchain.chat_models import AzureChatOpenAI
from langchain.llms import AzureOpenAI

logging.basicConfig(level=logging.ERROR)

from datetime import datetime, timedelta
from typing import List
from termcolor import colored

from langchain.docstore import InMemoryDocstore
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.retrievers import TimeWeightedVectorStoreRetriever


from langchain.experimental.generative_agents import GenerativeAgent, GenerativeAgentMemory

import math
import faiss


def relevance_score_fn(score: float) -> float:
    """Return a similarity score on a scale [0, 1]."""
    # This will differ depending on a few things:
    # - the distance / similarity metric used by the VectorStore
    # - the scale of your embeddings (OpenAI's are unit norm. Many others are not!)
    # This function converts the euclidean norm of normalized embeddings
    # (0 is most similar, sqrt(2) most dissimilar)
    # to a similarity function (0 to 1)
    return 1.0 - score / math.sqrt(2)


def create_new_memory_retriever():
    """Create a new vector store retriever unique to the agent."""
    # Define your embedding model
    embeddings_model = OpenAIEmbeddings(deployment="text-embedding-ada-002_deploy",  chunk_size=1)
    # Initialize the vectorstore as empty
    embedding_size = 1536
    index = faiss.IndexFlatL2(embedding_size)
    vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {}, relevance_score_fn=relevance_score_fn)
    return TimeWeightedVectorStoreRetriever(vectorstore=vectorstore, other_score_keys=["importance"], k=15)


USER_NAME = "Person A"  # The name you want to use when interviewing the agent.

LLM = AzureChatOpenAI(deployment_name="gpt-35-turbo", max_tokens=1500)

tommies_memory = GenerativeAgentMemory(
    llm=LLM,
    memory_retriever=create_new_memory_retriever(),
    verbose=True,
    reflection_threshold=8  # we will give this a relatively low number to show how reflection works
)

tommie = GenerativeAgent(name="Tommie",
                         age=25,
                         traits="anxious, likes design, talkative",  # You can add more persistent traits here
                         status="looking for a job",
                         # When connected to a virtual world, we can have the characters update their status
                         memory_retriever=create_new_memory_retriever(),
                         llm=LLM,
                         memory=tommies_memory
                         )

# The current "Summary" of a character can't be made because the agent hasn't made
# any observations yet.
print(tommie.get_summary())

Expected behavior

Just working