agent-zero
agent-zero copied to clipboard
frdel
LMStudio Embedding Error?
I'm trying to use the nomic embedding model in LM studio with this, and I noticed you have a get_lm_studio_embedding function so I assume it should work, right? I don't think it's the SSH because it looks like it retries until it succeeds, right? The llms just tell me something about not using the right class for ChatOpenAI or something but it's not super helpful.
I'm getting this error (Running on Linux btw)
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1723056146.323731 2447131 config.cc:230] gRPC experiments enabled: call_status_override_on_cancellation, event_engine_dns, event_engine_listener, http2_stats_fix, monitoring_experiment, pick_first_new, trace_record_callops, work_serializer_clears_time_cache
User message ('e' to leave):
>
Agent 0: Starting a message:
User intervention ('e' to leave, empty to continue):
> 'd like you to review the codebase in the working directory and see if you can do some market research into profitable products this can be developed into. Personality tests, personalized horoscope "vending machines", children's toys, etc. Figure out what people might want that isn't already on the market, that we could turn this into. Please put your findings into a subdirectory and ask me if you have any questions. Thank you.I0000 00:00:1723056150.779066 2447164 subchannel.cc:806] subchannel 0x7c6300005a60 {address=ipv6:%5B2607:f8b0:4009:819::200a%5D:443, args={grpc.client_channel_factory=0x5736c8206b20, grpc.default_authority=generativelanguage.googleapis.com:443, grpc.dns_enable_srv_queries=1, grpc.http2_scheme=https, grpc.internal.channel_credentials=0x5736c82490e0, grpc.internal.client_channel_call_destination=0x7c635ce4b3d0, grpc.internal.event_engine=0x7c6300003380, grpc.internal.security_connector=0x7c6300003230, grpc.internal.subchannel_pool=0x5736c8249bd0, grpc.max_receive_message_length=-1, grpc.max_send_message_length=-1, grpc.primary_user_agent=grpc-python/1.65.1, grpc.resource_quota=0x5736c824b490, grpc.server_uri=dns:///generativelanguage.googleapis.com:443}}: connect failed (UNKNOWN:connect: Network is unreachable (101) {created_time:"2024-08-07T13:42:30.778241714-05:00"}), backing off for 999 ms
Agent 0: Starting a message:
{
"thoughts": [
"The user has requested market research for profitable products based on the current codebase.",
"I will analyze the codebase to understand its capabilities and identify potential product ideas.",
"I will then conduct market research to determine the viability and profitability of these ideas.",
"Finally, I will document my findings in a subdirectory."
],
"tool_name": "code_execution_tool",
"tool_args": {
"runtime": "terminal",
"code": "mkdir market_research"
}
}
Agent 0: Using tool 'code_execution_tool':
Runtime: terminal
Code: mkdir market_research
Initializing docker container agent-zero-exe for safe code execution...
Started container with ID: 6780eb4e8a34a68b3059bb60f66a09ce89c0c302cbee961872eca5089a7a9ee1
Exception (client): Error reading SSH protocol banner[Errno 104] Connection reset by peer
Traceback (most recent call last):
File "/home/maxcurrent/.local/lib/python3.10/site-packages/paramiko/transport.py", line 2327, in _check_banner
buf = self.packetizer.readline(timeout)
File "/home/maxcurrent/.local/lib/python3.10/site-packages/paramiko/packet.py", line 381, in readline
buf += self._read_timeout(timeout)
File "/home/maxcurrent/.local/lib/python3.10/site-packages/paramiko/packet.py", line 616, in _read_timeout
x = self.__socket.recv(128)
ConnectionResetError: [Errno 104] Connection reset by peer
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/maxcurrent/.local/lib/python3.10/site-packages/paramiko/transport.py", line 2143, in run
self._check_banner()
File "/home/maxcurrent/.local/lib/python3.10/site-packages/paramiko/transport.py", line 2331, in _check_banner
raise SSHException(
paramiko.ssh_exception.SSHException: Error reading SSH protocol banner[Errno 104] Connection reset by peer
SSH Connection attempt 1...
Exception (client): Error reading SSH protocol banner[Errno 104] Connection reset by peer
Traceback (most recent call last):
File "/home/maxcurrent/.local/lib/python3.10/site-packages/paramiko/transport.py", line 2327, in _check_banner
buf = self.packetizer.readline(timeout)
File "/home/maxcurrent/.local/lib/python3.10/site-packages/paramiko/packet.py", line 381, in readline
buf += self._read_timeout(timeout)
File "/home/maxcurrent/.local/lib/python3.10/site-packages/paramiko/packet.py", line 616, in _read_timeout
x = self.__socket.recv(128)
ConnectionResetError: [Errno 104] Connection reset by peer
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/maxcurrent/.local/lib/python3.10/site-packages/paramiko/transport.py", line 2143, in run
self._check_banner()
File "/home/maxcurrent/.local/lib/python3.10/site-packages/paramiko/transport.py", line 2331, in _check_banner
raise SSHException(
paramiko.ssh_exception.SSHException: Error reading SSH protocol banner[Errno 104] Connection reset by peer
SSH Connection attempt 2...
Agent 0 code execution output:
mkdir: cannot create directory 'market_research': File exists
(venv) root@6780eb4e8a34:~#
Agent 0: Starting a message:
{
"thoughts": [
"The code execution tool reported that the directory 'market_research' already exists.",
"This means the directory was likely created in a previous interaction.",
"I will proceed with the market research and document my findings in the existing directory."
],
"tool_name": "knowledge_tool",
"tool_args": {
"question": "What are the capabilities of the codebase in the working directory?"
}
}
Agent 0: Using tool 'knowledge_tool':
Question: What are the capabilities of the codebase in the working directory?
Hint: No API key provided for Perplexity. Skipping Perplexity search.
Initializing VectorDB...
{
"system_error": "Traceback (most recent call last):
File "/home/maxcurrent/.local/lib/python3.10/site-packages/langchain_chroma/vectorstores.py", line 560, in similarity_search_with_score
query_embedding = self._embedding_function.embed_query(query)
File "/home/maxcurrent/.local/lib/python3.10/site-packages/langchain/embeddings/cache.py", line 194, in embed_query
return self.underlying_embeddings.embed_query(text)
AttributeError: 'ChatOpenAI' object has no attribute 'embed_query'
AttributeError: 'ChatOpenAI' object has no attribute 'embed_query'"
}
Anybody know what's going on there?
I used hugging face embedding model instead of lm studio and it solved my problem
I used hugging face embedding model instead of lm studio and it solved my problem
That's nice you solved your problem by going around an obstacle, but my problem persists as long as the LM-Studio embedding model doesn't work.
Hello! The problem is not just with LL-Studio, I'm facing the same issue trying to use embeddings with Ollama. Also Mistral Embeddings is broken. I was only able to use embeddings from OpenAi up to now (and good to know that HF also is working!).
