Error："Unknown request URL: POST /openai/v1/embeddings. Please check the URL for typos " when using groq API

[ouening]

It seems that the embedding did not work? How could I use different embedding model (like some models in ollama) instead of openai?

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\spyder_kernels\py3compat.py:356 in compat_exec
    exec(code, globals, locals)

  File d:\mega\misc\python\crewai\crewai_test.py:122
    result = crew.kickoff()

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\crewai\crew.py:252 in kickoff
    result = self._run_sequential_process()

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\crewai\crew.py:293 in _run_sequential_process
    output = task.execute(context=task_output)

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\crewai\task.py:173 in execute
    result = self._execute(

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\crewai\task.py:182 in _execute
    result = agent.execute_task(

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\crewai\agent.py:207 in execute_task
    memory = contextual_memory.build_context_for_task(task, context)

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\crewai\memory\contextual\contextual_memory.py:22 in build_context_for_task
    context.append(self._fetch_stm_context(query))

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\crewai\memory\contextual\contextual_memory.py:31 in _fetch_stm_context
    stm_results = self.stm.search(query)

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\crewai\memory\short_term\short_term_memory.py:23 in search
    return self.storage.search(query=query, score_threshold=score_threshold)

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\crewai\memory\storage\rag_storage.py:90 in search
    else self.app.search(query, limit)

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\embedchain\embedchain.py:635 in search
    return [{"context": c[0], "metadata": c[1]} for c in self.db.query(**params)]

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\embedchain\vectordb\chroma.py:220 in query
    result = self.collection.query(

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\chromadb\api\models\Collection.py:327 in query
    valid_query_embeddings = self._embed(input=valid_query_texts)

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\chromadb\api\models\Collection.py:633 in _embed
    return self._embedding_function(input=input)

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\chromadb\api\types.py:193 in __call__
    result = call(self, input)

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\chromadb\utils\embedding_functions.py:188 in __call__
    embeddings = self._client.create(

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\openai\resources\embeddings.py:113 in create
    return self._post(

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\openai\_base_client.py:1208 in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\openai\_base_client.py:897 in request
    return self._request(

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\openai\_base_client.py:988 in _request
    raise self._make_status_error_from_response(err.response) from None

NotFoundError: Error code: 404 - {'error': {'message': 'Unknown request URL: POST /openai/v1/embeddings. Please check the URL for typos, or see the docs at https://console.groq.com/docs/', 'type': 'invalid_request_error', 'code': 'unknown_url'}}

[rodrigo-campero]

You should override Open AI class with Groq stuff like:

import os

from crewai import Agent, Crew, Task
from dotenv import load_dotenv
from langchain_openai import ChatOpenAI

load_dotenv()

llm = ChatOpenAI(
    base_url=os.environ.get("GROQ_API_BASE"),
    api_key=os.environ.get("GROQ_API_KEY"),
    model=os.environ.get("GROQ_MODEL_NAME"),
    temperature=0,
)

general_agent = Agent(
    role="Math Professor",
    goal="""Provide the solution to the students that are asking mathematical questions and give them the answer.""",
    backstory="""You are an excellent math professor that likes to solve math questions in a way that everyone can understand your solution""",
    allow_delegation=False,
    verbose=True,
    llm=llm,
)
task = Task(description="""
            what is 3 + 5
            """, agent=general_agent, 
            expected_output="8")

crew = Crew(agents=[general_agent], tasks=[task], verbose=2)

result = crew.kickoff()

print(result)

env file:

GROQ_API_BASE=https://api.groq.com/openai/v1
GROQ_MODEL_NAME=llama3-70b-8192
GROQ_API_KEY=your-api-key

more info:

https://console.groq.com/docs/openai
https://docs.crewai.com/how-to/LLM-Connections/#ollama-integration

[ouening]

Thanks for your help! Your code runs well. But the code below still encounters problem:

import os
from crewai import Agent, Task, Crew, Process
from crewai_tools import DirectoryReadTool, FileReadTool, WebsiteSearchTool
from crewai_tools import SerperDevTool
from langchain_groq import ChatGroq
from langchain_openai import ChatOpenAI
from dotenv import load_dotenv

search_tool = SerperDevTool()

llm = ChatOpenAI(
    model = 'llama3-70b-8192' ,
    base_url = "https://api.groq.com/openai/v1",
    api_key = 'xxx'  ,
    temperature=0,
    )

print(llm.invoke("what is your knowledge cutoff?")) # for test

topic = 'AI in healthcare'

# Creating a senior researcher agent with memory and verbose mode
researcher = Agent(
  role='Senior Researcher',
  goal=f'Uncover groundbreaking technologies in {topic}',
  verbose=True,
  memory=True,
  backstory=(
    "Driven by curiosity, you're at the forefront of"
    "innovation, eager to explore and share knowledge that could change"
    "the world."
  ),
  # tools=[search_tool],
  allow_delegation=True,
   llm=llm
)

writer = Agent(
  role='Writer',
  goal=f'Narrate compelling tech stories about {topic}',
  verbose=True,
  memory=True,
  backstory=(
    "With a flair for simplifying complex topics, you craft"
    "engaging narratives that captivate and educate, bringing new"
    "discoveries to light in an accessible manner."
  ),
  # tools=[search_tool],
  allow_delegation=False,
  llm=llm
)

# Creating a writer agent with custom tools and delegation capability
# Research task
research_task = Task(
  description=(
    f"Identify the next big trend in {topic}."
    "Focus on identifying pros and cons and the overall narrative."
    "Your final report should clearly articulate the key points,"
    "its market opportunities, and potential risks."
  ),
  expected_output='A comprehensive 3 paragraphs long report on the latest AI trends.',
  # tools=[search_tool],
  agent=researcher,
)

# Writing task with language model configuration
write_task = Task(
  description=(
    f"Compose an insightful article on {topic}."
    "Focus on the latest trends and how it's impacting the industry."
    "This article should be easy to understand, engaging, and positive."
  ),
  expected_output=f'A 4 paragraph article on {topic} advancements formatted as markdown.',
  # tools=[search_tool],
  agent=writer,
  async_execution=False,
  output_file='new-blog-post.md'  # Example of output customization
)

# Forming the tech-focused crew with some enhanced configurations

crew = Crew(
  agents=[researcher, writer],
  tasks=[research_task, write_task],
  process=Process.sequential,  # Optional: Sequential task execution is default
  memory=True,
  cache=True,
  max_rpm=100,
  share_crew=True
)

# Starting the task execution process with enhanced feedback
result = crew.kickoff()
print(result)

Error message is:

Traceback (most recent call last):

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\spyder_kernels\py3compat.py:356 in compat_exec
    exec(code, globals, locals)

  File d:\mega\misc\python\crewai\crewai_test.py:122
    result = crew.kickoff()

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\crewai\crew.py:252 in kickoff
    result = self._run_sequential_process()

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\crewai\crew.py:293 in _run_sequential_process
    output = task.execute(context=task_output)

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\crewai\task.py:173 in execute
    result = self._execute(

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\crewai\task.py:182 in _execute
    result = agent.execute_task(

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\crewai\agent.py:207 in execute_task
    memory = contextual_memory.build_context_for_task(task, context)

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\crewai\memory\contextual\contextual_memory.py:22 in build_context_for_task
    context.append(self._fetch_stm_context(query))

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\crewai\memory\contextual\contextual_memory.py:31 in _fetch_stm_context
    stm_results = self.stm.search(query)

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\crewai\memory\short_term\short_term_memory.py:23 in search
    return self.storage.search(query=query, score_threshold=score_threshold)

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\crewai\memory\storage\rag_storage.py:90 in search
    else self.app.search(query, limit)

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\embedchain\embedchain.py:635 in search
    return [{"context": c[0], "metadata": c[1]} for c in self.db.query(**params)]

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\embedchain\vectordb\chroma.py:220 in query
    result = self.collection.query(

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\chromadb\api\models\Collection.py:327 in query
    valid_query_embeddings = self._embed(input=valid_query_texts)

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\chromadb\api\models\Collection.py:633 in _embed
    return self._embedding_function(input=input)

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\chromadb\api\types.py:193 in __call__
    result = call(self, input)

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\chromadb\utils\embedding_functions.py:188 in __call__
    embeddings = self._client.create(

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\openai\resources\embeddings.py:113 in create
    return self._post(

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\openai\_base_client.py:1208 in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\openai\_base_client.py:897 in request
    return self._request(

  File D:\Apps\WPy64-31131\python-3.11.3.amd64\Lib\site-packages\openai\_base_client.py:988 in _request
    raise self._make_status_error_from_response(err.response) from None

NotFoundError: Error code: 404 - {'error': {'message': 'Unknown request URL: POST /openai/v1/embeddings. Please check the URL for typos, or see the docs at https://console.groq.com/docs/', 'type': 'invalid_request_error', 'code': 'unknown_url'}}

I can't figure out what is the problem in my code.

[theCyberTech]

https://docs.crewai.com/core-concepts/Memory/#how-memory-systems-empower-agents - read this, you are using a non openai endpoint. by default memory uses Openai - you need to specify an embedding

[ouening]

It seems that Ollama's embedding, such as nomic-embed-text, is not currently supported. I tried using other free APIs, such as Gemini, but they all failed, and detailed documentation on the embedder is still lacking.

[theCyberTech]

correct, Embedchain is used for RAG / Memory and they do not currently support Ollama so that an issue that cannot be resolved by crewai. there is a PR for them to implement - embedchain/embedchain#1344

[ouening]

Thank you for your reply, I will continue to follow up.

[nkeilar]

Looks like it was just merged in and released... So hopefully soon we can have local embedding support. Which embedding model would we recommend as the default for ollama?

[joaomdmoura]

Yup, I'll make sure we update the dependency! :D