Inconsistency in how model name is supplied in the library.

[LindaLawton]

Description of the feature request:

Embedings requiers models/

result = genai.embed_content(
    model="models/embedding-001",
    content="What is the meaning of life?",
    task_type="retrieval_document",
    title="Embedding of single string")

# 1 input > 1 vector output
print(str(result['embedding'])[:50], '... TRIMMED]')

All other methos do not require it

  model = genai.GenerativeModel('gemini-1.5-flash')

What problem are you trying to solve with this feature?

Consistency

Any other information you'd like to share?

#justsaying