oramacore/config-docker.yaml at develop · oramasearch/oramacore · 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
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
http:
    host: 0.0.0.0
    port: 8080
    allow_cors: true
    with_prometheus: true

log:
    # Comment the following line to disable the logging
    file_path: "./log.log"

writer_side:
    output:
        type: in-memory
        # type: rabbitmq
        # host: localhost
        # port: 5672
        # user: guest
        # password: guest
        # v_host: /
        # stream_name: oramacore-operations
        # client_provided_name: oramacore-producer
        # producer_name: write

    hooks:
        select_embeddings_properties:
            check_interval: 60s
            max_idle_time: 20s
            instances_count_per_code: 3
            queue_capacity: 100
            max_execution_time: 1s
            max_startup_time: 100ms

    # Replace the following value with your own API key
    master_api_key: my-master-api-key
    config:
        data_dir: ./.data/writer
        # The maximum number of embeddings that can be stored in the queue
        # before the writer starts to be blocked
        # NB: the elements are in memory, so be careful with this value
        embedding_queue_limit: 50000
        # The number of the document insertions after the write side will commit the changes
        insert_batch_commit_size: 50000000
        # The default embedding model used to calculate the embeddings
        # if not specified in the collection creation
        default_embedding_model: BGESmall
        # The maximum number of request to javascript runtime that can be stored in the queue
        # NB: the elements are in memory, so be careful with this value
        javascript_queue_limit: 500000
        # Set interval for commiting the changes to the disk
        commit_interval: 1m

reader_side:
    input:
        type: in-memory
        # type: rabbitmq
        # host: localhost
        # port: 5672
        # user: guest
        # password: guest
        # v_host: /
        # stream_name: oramacore-operations
        # client_provided_name: oramacore-producer
        # consumer_name: reader

    config:
        data_dir: ./.data/reader
        # The number of the write operation after the read side will commit the changes
        insert_batch_commit_size: 50000000
        # Set interval for commiting the changes to the disk
        commit_interval: 1m

        # Per-collection commit thresholds
        # Uncomment to customize (these are the defaults)
        # collection_commit:
        #     # Number of operations before collection commits immediately
        #     operation_threshold: 300
        #     # Time since last commit before collection participates in global commit
        #     time_threshold: 5m

ai_server:
    scheme: http
    host: python-ai-server
    port: 50051
    api_key: ""
    max_connections: 15
    total_threads: 12

    embeddings:
        default_model_group: small
        dynamically_load_models: false
        execution_providers:
            - CUDAExecutionProvider
            - CPUExecutionProvider
        total_threads: 8

    llm:
        port: 8000
        host: vllm
        model: "Qwen/Qwen2.5-3B-Instruct"