jacobweiss2305
commented
1 year ago +1, I was using the default model in the repo: obrizum/all-MiniLM-L6-v2
Closed thisisloze closed 1 year ago
jacobweiss2305
commented
1 year ago +1, I was using the default model in the repo: obrizum/all-MiniLM-L6-v2
DaveMBush
commented
1 year ago That model seems to be corrupt currently.
I changed it to the one that is commented out (line above) and got past this error.
ie, in HuggingFaceEmbedding.py
model_id = "sentence-transformers/all-MiniLM-L6-v2"
# model_id = "obrizum/all-MiniLM-L6-v2"
api_url = f"https://api-inference.huggingface.co/pipeline/feature-extraction/{model_id}"
headers = {"Authorization": f"Bearer {hf_token}"}
dhnam
commented
1 year ago Check if you have included "HUGGINGFACE_TOKEN". Looks like this is necessary no matter what model you use.
Have you already searched for your ISSUE among the resolved ones?
What version of Python do you have?
What version of operating system do you have?
What type of installation did you perform?
Desktop (please complete the following information):
Describe the bug A clear and concise description of what the bug is. Traceback (most recent call last): File "/root/Free-AUTOGPT-with-NO-API/AUTOGPT.py", line 314, in
agent.run([input("Enter the objective of the AI system: (Be realistic!) ")])
File "/usr/local/lib/python3.10/dist-packages/langchain/experimental/autonomous_agents/autogpt/agent.py", line 91, in run
assistant_reply = self.chain.run(
File "/usr/local/lib/python3.10/dist-packages/langchain/chains/base.py", line 259, in run
return self(kwargs, callbacks=callbacks)[self.output_keys[0]]
File "/usr/local/lib/python3.10/dist-packages/langchain/chains/base.py", line 145, in call
raise e
File "/usr/local/lib/python3.10/dist-packages/langchain/chains/base.py", line 139, in call
self._call(inputs, run_manager=run_manager)
File "/usr/local/lib/python3.10/dist-packages/langchain/chains/llm.py", line 69, in _call
response = self.generate([inputs], run_manager=run_manager)
File "/usr/local/lib/python3.10/dist-packages/langchain/chains/llm.py", line 78, in generate
prompts, stop = self.prep_prompts(input_list, run_manager=run_manager)
File "/usr/local/lib/python3.10/dist-packages/langchain/chains/llm.py", line 106, in prep_prompts
prompt = self.prompt.format_prompt(selected_inputs)
File "/usr/local/lib/python3.10/dist-packages/langchain/prompts/chat.py", line 147, in format_prompt
messages = self.format_messages(kwargs)
File "/usr/local/lib/python3.10/dist-packages/langchain/experimental/autonomous_agents/autogpt/prompt.py", line 51, in format_messages
relevant_docs = memory.get_relevant_documents(str(previous_messages[-10:]))
File "/usr/local/lib/python3.10/dist-packages/langchain/vectorstores/base.py", line 392, in get_relevant_documents
docs = self.vectorstore.similarity_search(query, self.search_kwargs)
File "/usr/local/lib/python3.10/dist-packages/langchain/vectorstores/faiss.py", line 256, in similarity_search
docs_and_scores = self.similarity_search_with_score(query, k)
File "/usr/local/lib/python3.10/dist-packages/langchain/vectorstores/faiss.py", line 225, in similarity_search_with_score
embedding = self.embedding_function(query)
File "/root/Free-AUTOGPT-with-NO-API/Embedding/HuggingFaceEmbedding.py", line 39, in newEmbeddingFunction
embeddings = newEmbeddings(texts)
File "/usr/local/lib/python3.10/dist-packages/decorator.py", line 232, in fun
return caller(func, *(extras + args), *kw)
File "/usr/local/lib/python3.10/dist-packages/retry/api.py", line 73, in retry_decorator
return __retry_internal(partial(f, args, kwargs), exceptions, tries, delay, max_delay, backoff, jitter,
File "/usr/local/lib/python3.10/dist-packages/retry/api.py", line 33, in __retry_internal
return f()
File "/root/Free-AUTOGPT-with-NO-API/Embedding/HuggingFaceEmbedding.py", line 34, in newEmbeddings
raise RuntimeError(
RuntimeError: The model is currently loading, please re-run the query.
Screenshots If applicable, add screenshots to help explain your problem.
Additional context Add any other context about the problem here.