deepwiki-open/api/tools/embedder.py at 2af88f1ee821e6b55b3a5b5f8b7ec6ef920b90be · AsyncFuncAI/deepwiki-open · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
import adalflow as adal

from api.config import configs, get_embedder_type


def get_embedder(is_local_ollama: bool = False, use_google_embedder: bool = False, embedder_type: str = None) -> adal.Embedder:
    """Get embedder based on configuration or parameters.

    Args:
        is_local_ollama: Legacy parameter for Ollama embedder
        use_google_embedder: Legacy parameter for Google embedder
        embedder_type: Direct specification of embedder type ('ollama', 'google', 'bedrock', 'openai')

    Returns:
        adal.Embedder: Configured embedder instance
    """
    # Determine which embedder config to use
    if embedder_type:
        if embedder_type == 'ollama':
            embedder_config = configs["embedder_ollama"]
        elif embedder_type == 'google':
            embedder_config = configs["embedder_google"]
        elif embedder_type == 'bedrock':
            embedder_config = configs["embedder_bedrock"]
        elif embedder_type == 'azure':
            embedder_config = configs["embedder_azure"]
        else:  # default to openai
            embedder_config = configs["embedder"]
    elif is_local_ollama:
        embedder_config = configs["embedder_ollama"]
    elif use_google_embedder:
        embedder_config = configs["embedder_google"]
    else:
        # Auto-detect based on current configuration
        current_type = get_embedder_type()
        if current_type == 'bedrock':
            embedder_config = configs["embedder_bedrock"]
        elif current_type == 'ollama':
            embedder_config = configs["embedder_ollama"]
        elif current_type == 'google':
            embedder_config = configs["embedder_google"]
        elif current_type == 'azure':
            embedder_config = configs["embedder_azure"]
        else:
            embedder_config = configs["embedder"]

    # --- Initialize Embedder ---
    model_client_class = embedder_config["model_client"]
    if "initialize_kwargs" in embedder_config:
        model_client = model_client_class(**embedder_config["initialize_kwargs"])
    else:
        model_client = model_client_class()

    # Create embedder with basic parameters
    embedder_kwargs = {"model_client": model_client, "model_kwargs": embedder_config["model_kwargs"]}

    embedder = adal.Embedder(**embedder_kwargs)

    # Set batch_size as an attribute if available (not a constructor parameter)
    if "batch_size" in embedder_config:
        embedder.batch_size = embedder_config["batch_size"]
    return embedder