File size: 17,124 Bytes
447ebeb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
import os
import sys
import traceback

from dotenv import load_dotenv

load_dotenv()
import io
import os

sys.path.insert(
    0, os.path.abspath("../..")
)  # Adds the parent directory to the system path
import json

import pytest

import litellm
from litellm import RateLimitError, Timeout, completion, completion_cost, embedding
from unittest.mock import AsyncMock, patch
from litellm import RateLimitError, Timeout, completion, completion_cost, embedding
from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler

litellm.num_retries = 3


@pytest.mark.parametrize("stream", [True, False])
@pytest.mark.flaky(retries=3, delay=1)
@pytest.mark.asyncio
async def test_chat_completion_cohere_citations(stream):
    try:
        litellm.set_verbose = True
        messages = [
            {
                "role": "user",
                "content": "Which penguins are the tallest?",
            },
        ]
        response = await litellm.acompletion(
            model="cohere_chat/command-r",
            messages=messages,
            documents=[
                {"title": "Tall penguins", "text": "Emperor penguins are the tallest."},
                {
                    "title": "Penguin habitats",
                    "text": "Emperor penguins only live in Antarctica.",
                },
            ],
            stream=stream,
        )

        if stream:
            citations_chunk = False
            async for chunk in response:
                print("received chunk", chunk)
                if "citations" in chunk:
                    citations_chunk = True
                    break
            assert citations_chunk
        else:
            assert response.citations is not None
    except litellm.ServiceUnavailableError:
        pass
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")


def test_completion_cohere_command_r_plus_function_call():
    litellm.set_verbose = True
    tools = [
        {
            "type": "function",
            "function": {
                "name": "get_current_weather",
                "description": "Get the current weather in a given location",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "location": {
                            "type": "string",
                            "description": "The city and state, e.g. San Francisco, CA",
                        },
                        "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
                    },
                    "required": ["location"],
                },
            },
        }
    ]
    messages = [
        {
            "role": "user",
            "content": "What's the weather like in Boston today in Fahrenheit?",
        }
    ]
    try:
        # test without max tokens
        response = completion(
            model="command-r-plus",
            messages=messages,
            tools=tools,
            tool_choice="auto",
        )
        # Add any assertions, here to check response args
        print(response)
        assert isinstance(response.choices[0].message.tool_calls[0].function.name, str)
        assert isinstance(
            response.choices[0].message.tool_calls[0].function.arguments, str
        )

        messages.append(
            response.choices[0].message.model_dump()
        )  # Add assistant tool invokes
        tool_result = (
            '{"location": "Boston", "temperature": "72", "unit": "fahrenheit"}'
        )
        # Add user submitted tool results in the OpenAI format
        messages.append(
            {
                "tool_call_id": response.choices[0].message.tool_calls[0].id,
                "role": "tool",
                "name": response.choices[0].message.tool_calls[0].function.name,
                "content": tool_result,
            }
        )
        # In the second response, Cohere should deduce answer from tool results
        second_response = completion(
            model="command-r-plus",
            messages=messages,
            tools=tools,
            tool_choice="auto",
            force_single_step=True,
        )
        print(second_response)
    except litellm.Timeout:
        pass
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")


# @pytest.mark.skip(reason="flaky test, times out frequently")
@pytest.mark.flaky(retries=6, delay=1)
def test_completion_cohere():
    try:
        # litellm.set_verbose=True
        messages = [
            {"role": "system", "content": "You're a good bot"},
            {"role": "assistant", "content": [{"text": "2", "type": "text"}]},
            {"role": "assistant", "content": [{"text": "3", "type": "text"}]},
            {
                "role": "user",
                "content": "Hey",
            },
        ]
        response = completion(
            model="command-r",
            messages=messages,
        )
        print(response)
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")


# FYI - cohere_chat looks quite unstable, even when testing locally
@pytest.mark.asyncio
@pytest.mark.parametrize("sync_mode", [True, False])
@pytest.mark.flaky(retries=3, delay=1)
async def test_chat_completion_cohere(sync_mode):
    try:
        litellm.set_verbose = True
        messages = [
            {"role": "system", "content": "You're a good bot"},
            {
                "role": "user",
                "content": "Hey",
            },
        ]
        if sync_mode is False:
            response = await litellm.acompletion(
                model="cohere_chat/command-r",
                messages=messages,
                max_tokens=10,
            )
        else:
            response = completion(
                model="cohere_chat/command-r",
                messages=messages,
                max_tokens=10,
            )
        print(response)
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")


@pytest.mark.asyncio
@pytest.mark.parametrize("sync_mode", [False])
async def test_chat_completion_cohere_stream(sync_mode):
    try:
        litellm.set_verbose = True
        messages = [
            {"role": "system", "content": "You're a good bot"},
            {
                "role": "user",
                "content": "Hey",
            },
        ]
        if sync_mode is False:
            response = await litellm.acompletion(
                model="cohere_chat/command-r",
                messages=messages,
                max_tokens=10,
                stream=True,
            )
            print("async cohere stream response", response)
            async for chunk in response:
                print(chunk)
        else:
            response = completion(
                model="cohere_chat/command-r",
                messages=messages,
                max_tokens=10,
                stream=True,
            )
            print(response)
            for chunk in response:
                print(chunk)
    except litellm.APIConnectionError as e:
        pass
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")


@pytest.mark.asyncio
async def test_cohere_request_body_with_allowed_params():
    """
    Test to validate that when allowed_openai_params is provided, the request body contains
    the correct response_format and reasoning_effort values.
    """
    # Define test parameters
    test_response_format = {"type": "json"}
    test_reasoning_effort = "low"
    test_tools = [{
        "type": "function", 
        "function": {
            "name": "get_current_time", 
            "description": "Get the current time in a given location.", 
            "parameters": {
                "type": "object", 
                "properties": {
                    "location": {"type": "string", "description": "The city name, e.g. San Francisco"}
                },
                "required": ["location"]
            }
        }
    }]

    client = AsyncHTTPHandler()

    # Mock the post method
    with patch.object(client, "post", new=AsyncMock()) as mock_post:
        try:
            await litellm.acompletion(
                model="cohere/command",
                messages=[{"content": "what llm are you", "role": "user"}],
                allowed_openai_params=["tools", "response_format", "reasoning_effort"],
                response_format=test_response_format,
                reasoning_effort=test_reasoning_effort,
                tools=test_tools,
                client=client
            )
        except Exception:
            pass  # We only care about the request body validation

        # Verify the API call was made
        mock_post.assert_called_once()
        
        # Get and parse the request body
        request_data = json.loads(mock_post.call_args.kwargs["data"])
        print(f"request_data: {request_data}")
        
        # Validate request contains our specified parameters
        assert "allowed_openai_params" not in request_data
        assert request_data["response_format"] == test_response_format
        assert request_data["reasoning_effort"] == test_reasoning_effort


def test_cohere_embedding_outout_dimensions():
    litellm._turn_on_debug()
    response = embedding(model="cohere/embed-v4.0", input="Hello, world!", dimensions=512)
    print(f"response: {response}\n")
    assert len(response.data[0]["embedding"]) == 512


# Comprehensive Cohere Embed v4 tests
@pytest.mark.parametrize("sync_mode", [True, False])
@pytest.mark.asyncio
async def test_cohere_embed_v4_basic_text(sync_mode):
    """Test basic text embedding functionality with Cohere Embed v4."""
    try:
        data = {
            "model": "cohere/embed-v4.0",
            "input": ["Hello world!", "This is a test sentence."],
            "input_type": "search_document"
        }
        
        if sync_mode:
            response = embedding(**data)
        else:
            response = await litellm.aembedding(**data)
        
        # Validate response structure
        assert response.model is not None
        assert len(response.data) == 2
        assert response.data[0]['object'] == 'embedding'
        assert len(response.data[0]['embedding']) > 0
        assert response.usage.prompt_tokens > 0
        assert isinstance(response.usage, litellm.Usage)
        
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")


@pytest.mark.parametrize("sync_mode", [True, False])
@pytest.mark.asyncio
async def test_cohere_embed_v4_with_dimensions(sync_mode):
    """Test Cohere Embed v4 with specific dimension parameter."""
    try:
        data = {
            "model": "cohere/embed-v4.0",
            "input": ["Test with custom dimensions"],
            "dimensions": 512,
            "input_type": "search_query"
        }
        
        if sync_mode:
            response = embedding(**data)
        else:
            response = await litellm.aembedding(**data)
        
        # Validate dimension
        assert len(response.data[0]['embedding']) == 512
        assert isinstance(response.usage, litellm.Usage)
        
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")


@pytest.mark.parametrize("sync_mode", [True, False])
@pytest.mark.asyncio
async def test_cohere_embed_v4_image_embedding(sync_mode):
    """Test Cohere Embed v4 image embedding functionality (multimodal)."""
    try:
        import base64
        
        # 1x1 pixel red PNG (base64 encoded)
        test_image_data = b'\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x01\x00\x00\x00\x01\x08\x02\x00\x00\x00\x90wS\xde\x00\x00\x00\tpHYs\x00\x00\x0b\x13\x00\x00\x0b\x13\x01\x00\x9a\x9c\x18\x00\x00\x00\x0cIDATx\x9cc\xf8\x00\x00\x00\x01\x00\x01\x00\x00\x00\x00'
        test_image_b64 = base64.b64encode(test_image_data).decode('utf-8')
        
        data = {
            "model": "cohere/embed-v4.0",
            "input": [test_image_b64],
            "input_type": "image"
        }
        
        if sync_mode:
            response = embedding(**data)
        else:
            response = await litellm.aembedding(**data)
        
        # Validate response structure for image embedding
        assert response.model is not None
        assert len(response.data) == 1
        assert response.data[0]['object'] == 'embedding'
        assert len(response.data[0]['embedding']) > 0
        assert isinstance(response.usage, litellm.Usage)
        
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")


@pytest.mark.parametrize("input_type", ["search_document", "search_query", "classification", "clustering"])
@pytest.mark.asyncio
async def test_cohere_embed_v4_input_types(input_type):
    """Test Cohere Embed v4 with different input types."""
    try:
        response = await litellm.aembedding(
            model="cohere/embed-v4.0",
            input=[f"Test text for {input_type}"],
            input_type=input_type
        )
        
        assert response.model is not None
        assert len(response.data) == 1
        assert response.data[0]['object'] == 'embedding'
        assert len(response.data[0]['embedding']) > 0
        assert isinstance(response.usage, litellm.Usage)
        
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")


def test_cohere_embed_v4_encoding_format():
    """Test Cohere Embed v4 with different encoding formats."""
    try:
        response = embedding(
            model="cohere/embed-v4.0",
            input=["Test encoding format"],
            encoding_format="float"
        )
        
        assert response.model is not None
        assert len(response.data) == 1
        assert response.data[0]['object'] == 'embedding'
        assert len(response.data[0]['embedding']) > 0
        # Validate that embeddings are floats
        assert all(isinstance(x, float) for x in response.data[0]['embedding'])
        assert isinstance(response.usage, litellm.Usage)
        
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")


def test_cohere_embed_v4_error_handling():
    """Test error handling for Cohere Embed v4 with invalid inputs."""
    try:
        # Test with empty input - should raise an error
        try:
            response = embedding(
                model="cohere/embed-v4.0",
                input=[]  # Empty input
            )
            pytest.fail("Should have failed with empty input")
        except Exception:
            pass  # Expected to fail
        
        # Test with None input - should raise an error
        try:
            response = embedding(
                model="cohere/embed-v4.0",
                input=None
            )
            pytest.fail("Should have failed with None input")
        except Exception:
            pass  # Expected to fail
            
    except Exception as e:
        pytest.fail(f"Error in error handling test: {e}")


@pytest.mark.parametrize("sync_mode", [True, False])
@pytest.mark.asyncio
async def test_cohere_embed_v4_multiple_texts(sync_mode):
    """Test Cohere Embed v4 with multiple text inputs."""
    try:
        texts = [
            "The quick brown fox jumps over the lazy dog",
            "Machine learning is transforming the world",
            "Python is a versatile programming language",
            "Natural language processing enables human-computer interaction"
        ]
        
        data = {
            "model": "cohere/embed-v4.0",
            "input": texts,
            "input_type": "search_document"
        }
        
        if sync_mode:
            response = embedding(**data)
        else:
            response = await litellm.aembedding(**data)
        
        # Validate response structure
        assert response.model is not None
        assert len(response.data) == len(texts)
        
        for i, data_item in enumerate(response.data):
            assert data_item['object'] == 'embedding'
            assert data_item['index'] == i
            assert len(data_item['embedding']) > 0
            assert all(isinstance(x, float) for x in data_item['embedding'])
        
        assert isinstance(response.usage, litellm.Usage)
        assert response.usage.prompt_tokens > 0
        
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")


def test_cohere_embed_v4_with_optional_params():
    """Test Cohere Embed v4 with various optional parameters."""
    try:
        response = embedding(
            model="cohere/embed-v4.0",
            input=["Test with optional parameters"],
            input_type="search_query",
            dimensions=256,
            encoding_format="float"
        )
        
        # Validate response
        assert response.model is not None
        assert len(response.data) == 1
        assert response.data[0]['object'] == 'embedding'
        assert len(response.data[0]['embedding']) == 256  # Custom dimensions
        assert all(isinstance(x, float) for x in response.data[0]['embedding'])
        assert isinstance(response.usage, litellm.Usage)
        
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")