File size: 10,063 Bytes
e3278e4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
from typing import List, Optional, Union

from openai import OpenAI

import litellm
from litellm.llms.custom_httpx.http_handler import (
    AsyncHTTPHandler,
    HTTPHandler,
    get_async_httpx_client,
)
from litellm.llms.openai.openai import OpenAIChatCompletion
from litellm.types.llms.azure_ai import ImageEmbeddingRequest
from litellm.types.utils import EmbeddingResponse
from litellm.utils import convert_to_model_response_object

from .cohere_transformation import AzureAICohereConfig


class AzureAIEmbedding(OpenAIChatCompletion):

    def _process_response(
        self,
        image_embedding_responses: Optional[List],
        text_embedding_responses: Optional[List],
        image_embeddings_idx: List[int],
        model_response: EmbeddingResponse,
        input: List,
    ):
        combined_responses = []
        if (
            image_embedding_responses is not None
            and text_embedding_responses is not None
        ):
            # Combine and order the results
            text_idx = 0
            image_idx = 0

            for idx in range(len(input)):
                if idx in image_embeddings_idx:
                    combined_responses.append(image_embedding_responses[image_idx])
                    image_idx += 1
                else:
                    combined_responses.append(text_embedding_responses[text_idx])
                    text_idx += 1

            model_response.data = combined_responses
        elif image_embedding_responses is not None:
            model_response.data = image_embedding_responses
        elif text_embedding_responses is not None:
            model_response.data = text_embedding_responses

        response = AzureAICohereConfig()._transform_response(response=model_response)  # type: ignore

        return response

    async def async_image_embedding(
        self,
        model: str,
        data: ImageEmbeddingRequest,
        timeout: float,
        logging_obj,
        model_response: litellm.EmbeddingResponse,
        optional_params: dict,
        api_key: Optional[str],
        api_base: Optional[str],
        client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
    ) -> EmbeddingResponse:
        if client is None or not isinstance(client, AsyncHTTPHandler):
            client = get_async_httpx_client(
                llm_provider=litellm.LlmProviders.AZURE_AI,
                params={"timeout": timeout},
            )

        url = "{}/images/embeddings".format(api_base)

        response = await client.post(
            url=url,
            json=data,  # type: ignore
            headers={"Authorization": "Bearer {}".format(api_key)},
        )

        embedding_response = response.json()
        embedding_headers = dict(response.headers)
        returned_response: EmbeddingResponse = convert_to_model_response_object(  # type: ignore
            response_object=embedding_response,
            model_response_object=model_response,
            response_type="embedding",
            stream=False,
            _response_headers=embedding_headers,
        )
        return returned_response

    def image_embedding(
        self,
        model: str,
        data: ImageEmbeddingRequest,
        timeout: float,
        logging_obj,
        model_response: EmbeddingResponse,
        optional_params: dict,
        api_key: Optional[str],
        api_base: Optional[str],
        client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
    ):
        if api_base is None:
            raise ValueError(
                "api_base is None. Please set AZURE_AI_API_BASE or dynamically via `api_base` param, to make the request."
            )
        if api_key is None:
            raise ValueError(
                "api_key is None. Please set AZURE_AI_API_KEY or dynamically via `api_key` param, to make the request."
            )

        if client is None or not isinstance(client, HTTPHandler):
            client = HTTPHandler(timeout=timeout, concurrent_limit=1)

        url = "{}/images/embeddings".format(api_base)

        response = client.post(
            url=url,
            json=data,  # type: ignore
            headers={"Authorization": "Bearer {}".format(api_key)},
        )

        embedding_response = response.json()
        embedding_headers = dict(response.headers)
        returned_response: EmbeddingResponse = convert_to_model_response_object(  # type: ignore
            response_object=embedding_response,
            model_response_object=model_response,
            response_type="embedding",
            stream=False,
            _response_headers=embedding_headers,
        )
        return returned_response

    async def async_embedding(
        self,
        model: str,
        input: List,
        timeout: float,
        logging_obj,
        model_response: litellm.EmbeddingResponse,
        optional_params: dict,
        api_key: Optional[str] = None,
        api_base: Optional[str] = None,
        client=None,
    ) -> EmbeddingResponse:

        (
            image_embeddings_request,
            v1_embeddings_request,
            image_embeddings_idx,
        ) = AzureAICohereConfig()._transform_request(
            input=input, optional_params=optional_params, model=model
        )

        image_embedding_responses: Optional[List] = None
        text_embedding_responses: Optional[List] = None

        if image_embeddings_request["input"]:
            image_response = await self.async_image_embedding(
                model=model,
                data=image_embeddings_request,
                timeout=timeout,
                logging_obj=logging_obj,
                model_response=model_response,
                optional_params=optional_params,
                api_key=api_key,
                api_base=api_base,
                client=client,
            )

            image_embedding_responses = image_response.data
            if image_embedding_responses is None:
                raise Exception("/image/embeddings route returned None Embeddings.")

        if v1_embeddings_request["input"]:
            response: EmbeddingResponse = await super().embedding(  # type: ignore
                model=model,
                input=input,
                timeout=timeout,
                logging_obj=logging_obj,
                model_response=model_response,
                optional_params=optional_params,
                api_key=api_key,
                api_base=api_base,
                client=client,
                aembedding=True,
            )
            text_embedding_responses = response.data
            if text_embedding_responses is None:
                raise Exception("/v1/embeddings route returned None Embeddings.")

        return self._process_response(
            image_embedding_responses=image_embedding_responses,
            text_embedding_responses=text_embedding_responses,
            image_embeddings_idx=image_embeddings_idx,
            model_response=model_response,
            input=input,
        )

    def embedding(
        self,
        model: str,
        input: List,
        timeout: float,
        logging_obj,
        model_response: EmbeddingResponse,
        optional_params: dict,
        api_key: Optional[str] = None,
        api_base: Optional[str] = None,
        client=None,
        aembedding=None,
        max_retries: Optional[int] = None,
    ) -> EmbeddingResponse:
        """
        - Separate image url from text
        -> route image url call to `/image/embeddings`
        -> route text call to `/v1/embeddings` (OpenAI route)

        assemble result in-order, and return
        """
        if aembedding is True:
            return self.async_embedding(  # type: ignore
                model,
                input,
                timeout,
                logging_obj,
                model_response,
                optional_params,
                api_key,
                api_base,
                client,
            )

        (
            image_embeddings_request,
            v1_embeddings_request,
            image_embeddings_idx,
        ) = AzureAICohereConfig()._transform_request(
            input=input, optional_params=optional_params, model=model
        )

        image_embedding_responses: Optional[List] = None
        text_embedding_responses: Optional[List] = None

        if image_embeddings_request["input"]:
            image_response = self.image_embedding(
                model=model,
                data=image_embeddings_request,
                timeout=timeout,
                logging_obj=logging_obj,
                model_response=model_response,
                optional_params=optional_params,
                api_key=api_key,
                api_base=api_base,
                client=client,
            )

            image_embedding_responses = image_response.data
            if image_embedding_responses is None:
                raise Exception("/image/embeddings route returned None Embeddings.")

        if v1_embeddings_request["input"]:
            response: EmbeddingResponse = super().embedding(  # type: ignore
                model,
                input,
                timeout,
                logging_obj,
                model_response,
                optional_params,
                api_key,
                api_base,
                client=(
                    client
                    if client is not None and isinstance(client, OpenAI)
                    else None
                ),
                aembedding=aembedding,
            )

            text_embedding_responses = response.data
            if text_embedding_responses is None:
                raise Exception("/v1/embeddings route returned None Embeddings.")

        return self._process_response(
            image_embedding_responses=image_embedding_responses,
            text_embedding_responses=text_embedding_responses,
            image_embeddings_idx=image_embeddings_idx,
            model_response=model_response,
            input=input,
        )