File size: 7,320 Bytes
3943768
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
"""OpenAI chat wrapper."""

from __future__ import annotations

from typing import (
    Any,
    AsyncIterator,
    Iterator,
    List,
    Optional,
    Union,
)

from langchain_community.chat_models import ChatOpenAI, AzureChatOpenAI
from langchain_community.chat_models.openai import acompletion_with_retry, _convert_delta_to_message_chunk
from langchain_core.callbacks import (
    AsyncCallbackManagerForLLMRun,
    CallbackManagerForLLMRun,
)
from langchain_core.language_models.chat_models import (
    agenerate_from_stream,
    generate_from_stream,
)
from langchain_core.messages import (
    AIMessageChunk,
    BaseMessage,
)
from langchain_core.outputs import ChatGeneration, ChatGenerationChunk, ChatResult
from langchain_core.pydantic_v1 import BaseModel

from langchain_community.adapters.openai import (
    convert_dict_to_message,
)


class H2OBaseChatOpenAI:
    def _stream(
        self,
        messages: List[BaseMessage],
        stop: Optional[List[str]] = None,
        run_manager: Optional[CallbackManagerForLLMRun] = None,
        **kwargs: Any,
    ) -> Iterator[ChatGenerationChunk]:
        message_dicts, params = self._create_message_dicts(messages, stop)
        params = {**params, **kwargs, "stream": True}

        default_chunk_class = AIMessageChunk
        for chunk in self.completion_with_retry(
            messages=message_dicts, run_manager=run_manager, **params
        ):
            if not isinstance(chunk, dict):
                chunk = chunk.dict()
            if len(chunk["choices"]) == 0:
                continue
            choice = chunk["choices"][0]
            chunk = _convert_delta_to_message_chunk(
                choice["delta"], default_chunk_class
            )
            finish_reason = choice.get("finish_reason")
            generation_info = (
                dict(finish_reason=finish_reason) if finish_reason is not None else None
            )
            default_chunk_class = chunk.__class__
            cg_chunk = ChatGenerationChunk(
                message=chunk, generation_info=generation_info
            )
            cg_chunk = self.mod_cg_chunk(cg_chunk)
            if run_manager:
                run_manager.on_llm_new_token(cg_chunk.text, chunk=cg_chunk)
            yield cg_chunk

    def mod_cg_chunk(self, cg_chunk: ChatGenerationChunk) -> ChatGenerationChunk:
        if 'tools' in self.model_kwargs and self.model_kwargs['tools']:
            if 'tool_calls' in cg_chunk.message.additional_kwargs:
                cg_chunk.message.content = cg_chunk.text = cg_chunk.message.additional_kwargs['tool_calls'][0]['function']['arguments']
            else:
                cg_chunk.text = ''
        return cg_chunk

    def _generate(
        self,
        messages: List[BaseMessage],
        stop: Optional[List[str]] = None,
        run_manager: Optional[CallbackManagerForLLMRun] = None,
        stream: Optional[bool] = None,
        **kwargs: Any,
    ) -> ChatResult:
        should_stream = stream if stream is not None else self.streaming
        if should_stream:
            stream_iter = self._stream(
                messages, stop=stop, run_manager=run_manager, **kwargs
            )
            return generate_from_stream(stream_iter)
        message_dicts, params = self._create_message_dicts(messages, stop)
        params = {
            **params,
            **({"stream": stream} if stream is not None else {}),
            **kwargs,
        }
        response = self.completion_with_retry(
            messages=message_dicts, run_manager=run_manager, **params
        )
        return self._create_chat_result(response)

    def _create_chat_result(self, response: Union[dict, BaseModel]) -> ChatResult:
        generations = []
        if not isinstance(response, dict):
            response = response.dict()
        for res in response["choices"]:
            message = convert_dict_to_message(res["message"])

            if 'tools' in self.model_kwargs and self.model_kwargs['tools']:
                if 'tool_calls' in message.additional_kwargs:
                    message.content = ''.join([x['function']['arguments'] for x in message.additional_kwargs['tool_calls']])

            generation_info = dict(finish_reason=res.get("finish_reason"))
            if "logprobs" in res:
                generation_info["logprobs"] = res["logprobs"]
            gen = ChatGeneration(
                message=message,
                generation_info=generation_info,
            )
            generations.append(gen)
        token_usage = response.get("usage", {})
        llm_output = {
            "token_usage": token_usage,
            "model_name": self.model_name,
            "system_fingerprint": response.get("system_fingerprint", ""),
        }
        return ChatResult(generations=generations, llm_output=llm_output)

    async def _astream(
        self,
        messages: List[BaseMessage],
        stop: Optional[List[str]] = None,
        run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
        **kwargs: Any,
    ) -> AsyncIterator[ChatGenerationChunk]:
        message_dicts, params = self._create_message_dicts(messages, stop)
        params = {**params, **kwargs, "stream": True}

        default_chunk_class = AIMessageChunk
        async for chunk in await acompletion_with_retry(
            self, messages=message_dicts, run_manager=run_manager, **params
        ):
            if not isinstance(chunk, dict):
                chunk = chunk.dict()
            if len(chunk["choices"]) == 0:
                continue
            choice = chunk["choices"][0]
            chunk = _convert_delta_to_message_chunk(
                choice["delta"], default_chunk_class
            )
            finish_reason = choice.get("finish_reason")
            generation_info = (
                dict(finish_reason=finish_reason) if finish_reason is not None else None
            )
            default_chunk_class = chunk.__class__
            cg_chunk = ChatGenerationChunk(
                message=chunk, generation_info=generation_info
            )
            cg_chunk = self.mod_cg_chunk(cg_chunk)
            if run_manager:
                await run_manager.on_llm_new_token(token=cg_chunk.text, chunk=cg_chunk)
            yield cg_chunk

    async def _agenerate(
        self,
        messages: List[BaseMessage],
        stop: Optional[List[str]] = None,
        run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
        stream: Optional[bool] = None,
        **kwargs: Any,
    ) -> ChatResult:
        should_stream = stream if stream is not None else self.streaming
        if should_stream:
            stream_iter = self._astream(
                messages, stop=stop, run_manager=run_manager, **kwargs
            )
            return await agenerate_from_stream(stream_iter)

        message_dicts, params = self._create_message_dicts(messages, stop)
        params = {
            **params,
            **({"stream": stream} if stream is not None else {}),
            **kwargs,
        }
        response = await acompletion_with_retry(
            self, messages=message_dicts, run_manager=run_manager, **params
        )
        return self._create_chat_result(response)


class H2OBaseAzureChatOpenAI(H2OBaseChatOpenAI, AzureChatOpenAI):
    pass