h2ogpt/src/enums.py at main · encycdata/h2ogpt · 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
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
from enum import Enum


class PromptType(Enum):
    custom = -1
    plain = 0
    instruct = 1
    quality = 2
    human_bot = 3
    dai_faq = 4
    summarize = 5
    simple_instruct = 6
    instruct_vicuna = 7
    instruct_with_end = 8
    human_bot_orig = 9
    prompt_answer = 10
    open_assistant = 11
    wizard_lm = 12
    wizard_mega = 13
    instruct_vicuna2 = 14
    instruct_vicuna3 = 15
    wizard2 = 16
    wizard3 = 17
    instruct_simple = 18
    wizard_vicuna = 19
    openai = 20
    openai_chat = 21
    gptj = 22
    prompt_answer_openllama = 23
    vicuna11 = 24
    mptinstruct = 25
    mptchat = 26
    falcon = 27
    guanaco = 28
    llama2 = 29
    beluga = 30
    wizard3nospace = 31


class DocumentSubset(Enum):
    Relevant = 0
    RelSources = 1
    TopKSources = 2


non_query_commands = [
    DocumentSubset.RelSources.name,
    DocumentSubset.TopKSources.name
]


class DocumentChoice(Enum):
    ALL = 'All'


class LangChainMode(Enum):
    """LangChain mode"""

    DISABLED = "Disabled"
    LLM = "LLM"
    WIKI = "wiki"
    WIKI_FULL = "wiki_full"
    USER_DATA = "UserData"
    MY_DATA = "MyData"
    GITHUB_H2OGPT = "github h2oGPT"
    H2O_DAI_DOCS = "DriverlessAI docs"


class LangChainTypes(Enum):
    SHARED = 'shared'
    PERSONAL = 'personal'


# modes should not be removed from visible list or added by name
langchain_modes_intrinsic = [LangChainMode.DISABLED.value,
                             LangChainMode.LLM.value,
                             LangChainMode.MY_DATA.value]

langchain_modes_non_db = [LangChainMode.DISABLED.value,
                          LangChainMode.LLM.value]


class LangChainAction(Enum):
    """LangChain action"""

    QUERY = "Query"
    # WIP:
    # SUMMARIZE_MAP = "Summarize_map_reduce"
    SUMMARIZE_MAP = "Summarize"
    SUMMARIZE_ALL = "Summarize_all"
    SUMMARIZE_REFINE = "Summarize_refine"


class LangChainAgent(Enum):
    """LangChain agents"""

    SEARCH = "Search"
    # CSV = "csv"  # WIP


no_server_str = no_lora_str = no_model_str = '[None/Remove]'

# from site-packages/langchain/llms/openai.py
# but needed since ChatOpenAI doesn't have this information
model_token_mapping = {
    "gpt-4": 8192,
    "gpt-4-0314": 8192,
    "gpt-4-32k": 32768,
    "gpt-4-32k-0314": 32768,
    "gpt-3.5-turbo": 4096,
    "gpt-3.5-turbo-16k": 16 * 1024,
    "gpt-3.5-turbo-0301": 4096,
    "text-ada-001": 2049,
    "ada": 2049,
    "text-babbage-001": 2040,
    "babbage": 2049,
    "text-curie-001": 2049,
    "curie": 2049,
    "davinci": 2049,
    "text-davinci-003": 4097,
    "text-davinci-002": 4097,
    "code-davinci-002": 8001,
    "code-davinci-001": 8001,
    "code-cushman-002": 2048,
    "code-cushman-001": 2048,
}

source_prefix = "Sources [Score | Link]:"
source_postfix = "End Sources<p>"