Mustangs007

issue with below code

4

from crewai import Agent, Task, Crew from langchain_openai import ChatOpenAI import os os.environ["OPENAI_API_KEY"] = "NA" llm = ChatOpenAI( model = "crewai-llama2", base_url = "http://localhost:11434/v1") general_agent = Agent(role = "Math Professor",...

error in apple mac m3

2

import mlx.core as mx generation_output = model.generate( mx.array(input_tokens['input_ids']), max_new_tokens=3, use_cache=True, return_dict_in_generate=True) print(generation_output) error : [load] Input must be a file-like object opened in binary mode, or string

Issue in reading through csv file using OLLAMA

6

from crewai_tools import CSVSearchTool tool = CSVSearchTool(csv='record.csv', config=dict( llm=dict( provider="ollama", config=dict( model="llama2", # temperature=0.5, # top_p=1, # stream=true, ), ), embedder=dict( provider="ollama", config=dict( model="llama2", #task_type="retrieval_document", # title="Embeddings", ), ), )...

HI team, can anyone please provide sample simple example which utilize CSV Rag and locall ollama. thanks in advance.

Phi-3-mini-4k-instruct : Failing to stop at <|end|> on generating the answer.

4

```python from mlx_lm import load, generate model, tokenizer = load(path_or_hf_repo = phi3_path,#,tokenizer_config=tokenizer_config # adapter_path = adapt_path, tokenizer_config={"trust_remote_code": True}) messages = [ {"role": "user", "content": 'Where is delhi, explain it only...