openlit 1.34.14__py3-none-any.whl → 1.34.16__py3-none-any.whl

openlit/instrumentation/litellm/utils.py

@@ -0,0 +1,288 @@
+"""
+LiteLLM OpenTelemetry instrumentation utility functions
+"""
+import time
+
+from opentelemetry.trace import Status, StatusCode
+
+from openlit.__helpers import (
+    calculate_ttft,
+    response_as_dict,
+    calculate_tbt,
+    get_chat_model_cost,
+    get_embed_model_cost,
+    common_span_attributes,
+    record_completion_metrics,
+    record_embedding_metrics,
+)
+from openlit.semcov import SemanticConvention
+
+def format_content(messages):
+    """
+    Process a list of messages to extract content.
+    """
+
+    formatted_messages = []
+    for message in messages:
+        role = message['role']
+        content = message['content']
+
+        if isinstance(content, list):
+            content_str = ", ".join(
+                f'{item["type"]}: {item["text"] if "text" in item else item["image_url"]}'
+                if "type" in item else f'text: {item["text"]}'
+                for item in content
+            )
+            formatted_messages.append(f'{role}: {content_str}')
+        else:
+            formatted_messages.append(f'{role}: {content}')
+
+    return '\n'.join(formatted_messages)
+
+def process_chunk(scope, chunk):
+    """
+    Process a chunk of response data and update state.
+    """
+
+    end_time = time.time()
+    # Record the timestamp for the current chunk
+    scope._timestamps.append(end_time)
+
+    if len(scope._timestamps) == 1:
+        # Calculate time to first chunk
+        scope._ttft = calculate_ttft(scope._timestamps, scope._start_time)
+
+    chunked = response_as_dict(chunk)
+
+    # Collect message IDs and aggregated response from events
+    if (len(chunked.get('choices', [])) > 0 and ('delta' in chunked.get('choices')[0] and
+        'content' in chunked.get('choices')[0].get('delta', {}))):
+
+        content = chunked.get('choices')[0].get('delta').get('content')
+        if content:
+            scope._llmresponse += content
+
+        # Handle tool calls in streaming - optimized
+        delta_tools = chunked.get('choices', [{}])[0].get('delta', {}).get('tool_calls')
+        if delta_tools:
+            scope._tools = scope._tools or []
+
+            for tool in delta_tools:
+                idx = tool.get('index', 0)
+
+                # Extend list if needed
+                scope._tools.extend([{}] * (idx + 1 - len(scope._tools)))
+
+                if tool.get('id'):  # New tool (id exists)
+                    func = tool.get('function', {})
+                    scope._tools[idx] = {
+                        'id': tool['id'],
+                        'function': {'name': func.get('name', ''), 'arguments': func.get('arguments', '')},
+                        'type': tool.get('type', 'function')
+                    }
+                elif scope._tools[idx] and 'function' in tool:  # Append args (id is None)
+                    scope._tools[idx]['function']['arguments'] += tool['function'].get('arguments', '')
+
+    if chunked.get('usage'):
+        scope._input_tokens = chunked.get('usage').get('prompt_tokens', 0)
+        scope._output_tokens = chunked.get('usage').get('completion_tokens', 0)
+        scope._response_id = chunked.get('id')
+        scope._response_model = chunked.get('model')
+        scope._finish_reason = chunked.get('choices', [{}])[0].get('finish_reason')
+        scope._response_service_tier = str(chunked.get('system_fingerprint', ''))
+        scope._end_time = time.time()
+
+def common_chat_logic(scope, pricing_info, environment, application_name, metrics,
+    capture_message_content, disable_metrics, version, is_stream):
+    """
+    Process chat request and generate Telemetry
+    """
+
+    if len(scope._timestamps) > 1:
+        scope._tbt = calculate_tbt(scope._timestamps)
+
+    prompt = format_content(scope._kwargs.get('messages', []))
+    request_model = scope._kwargs.get('model', 'openai/gpt-4o')
+
+    cost = get_chat_model_cost(request_model, pricing_info, scope._input_tokens, scope._output_tokens)
+
+    # Common Span Attributes
+    common_span_attributes(scope,
+        SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT, SemanticConvention.GEN_AI_SYSTEM_LITELLM,
+        scope._server_address, scope._server_port, request_model, scope._response_model,
+        environment, application_name, is_stream, scope._tbt, scope._ttft, version)
+
+    # Span Attributes for Request parameters
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_SEED, scope._kwargs.get('seed', ''))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_FREQUENCY_PENALTY, scope._kwargs.get('frequency_penalty', 0.0))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_MAX_TOKENS, scope._kwargs.get('max_tokens', -1))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_PRESENCE_PENALTY, scope._kwargs.get('presence_penalty', 0.0))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_STOP_SEQUENCES, scope._kwargs.get('stop', []))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TEMPERATURE, scope._kwargs.get('temperature', 1.0))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TOP_P, scope._kwargs.get('top_p', 1.0))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_USER, scope._kwargs.get('user', ''))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_SERVICE_TIER, scope._kwargs.get('service_tier', 'auto'))
+
+    # Span Attributes for Response parameters
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_ID, scope._response_id)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_FINISH_REASON, [scope._finish_reason])
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_SERVICE_TIER, scope._response_service_tier)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_SYSTEM_FINGERPRINT, scope._response_service_tier)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_OUTPUT_TYPE, "text" if isinstance(scope._llmresponse, str) else "json")
+
+    # Span Attributes for Cost and Tokens
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_INPUT_TOKENS, scope._input_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_OUTPUT_TOKENS, scope._output_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_CLIENT_TOKEN_USAGE, scope._input_tokens + scope._output_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_COST, cost)
+
+    # Span Attributes for Tools - optimized
+    if scope._tools:
+        tools = scope._tools if isinstance(scope._tools, list) else [scope._tools]
+
+        names, ids, args = zip(*[
+            (t.get("function", {}).get("name", ""),
+             str(t.get("id", "")),
+             str(t.get("function", {}).get("arguments", "")))
+            for t in tools if isinstance(t, dict) and t
+        ]) if tools else ([], [], [])
+
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_NAME, ", ".join(filter(None, names)))
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_CALL_ID, ", ".join(filter(None, ids)))
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_ARGS, ", ".join(filter(None, args)))
+
+    # Span Attributes for Content
+    if capture_message_content:
+        scope._span.set_attribute(SemanticConvention.GEN_AI_CONTENT_PROMPT, prompt)
+        scope._span.set_attribute(SemanticConvention.GEN_AI_CONTENT_COMPLETION, scope._llmresponse)
+
+        # To be removed once the change to span_attributes (from span events) is complete
+        scope._span.add_event(
+            name=SemanticConvention.GEN_AI_CONTENT_PROMPT_EVENT,
+            attributes={
+                SemanticConvention.GEN_AI_CONTENT_PROMPT: prompt,
+            },
+        )
+        scope._span.add_event(
+            name=SemanticConvention.GEN_AI_CONTENT_COMPLETION_EVENT,
+            attributes={
+                SemanticConvention.GEN_AI_CONTENT_COMPLETION: scope._llmresponse,
+            },
+        )
+
+    scope._span.set_status(Status(StatusCode.OK))
+
+    # Metrics
+    if not disable_metrics:
+        record_completion_metrics(metrics, SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT, SemanticConvention.GEN_AI_SYSTEM_LITELLM,
+            scope._server_address, scope._server_port, request_model, scope._response_model, environment,
+            application_name, scope._start_time, scope._end_time, scope._input_tokens, scope._output_tokens,
+            cost, scope._tbt, scope._ttft)
+
+def process_streaming_chat_response(scope, pricing_info, environment, application_name, metrics,
+    capture_message_content=False, disable_metrics=False, version=""):
+    """
+    Process streaming chat request and generate Telemetry
+    """
+
+    common_chat_logic(scope, pricing_info, environment, application_name, metrics,
+        capture_message_content, disable_metrics, version, is_stream=True)
+
+def process_chat_response(response, request_model, pricing_info, server_port, server_address,
+    environment, application_name, metrics, start_time, span, capture_message_content=False,
+    disable_metrics=False, version="1.0.0", **kwargs):
+    """
+    Process chat request and generate Telemetry
+    """
+
+    # Create scope object
+    scope = type("GenericScope", (), {})()
+    response_dict = response_as_dict(response)
+
+    scope._start_time = start_time
+    scope._end_time = time.time()
+    scope._span = span
+    scope._llmresponse = " ".join(
+        (choice.get("message", {}).get("content") or "")
+        for choice in response_dict.get("choices", [])
+    )
+    scope._input_tokens = response_dict.get('usage', {}).get('prompt_tokens', 0)
+    scope._output_tokens = response_dict.get('usage', {}).get('completion_tokens', 0)
+    scope._response_id = response_dict.get('id')
+    scope._response_model = response_dict.get('model')
+    scope._finish_reason = str(response_dict.get('choices', [])[0].get('finish_reason', ''))
+    scope._response_service_tier = str(response_dict.get('system_fingerprint', ''))
+    scope._timestamps = []
+    scope._ttft, scope._tbt = scope._end_time - scope._start_time, 0
+    scope._server_address, scope._server_port = server_address, server_port
+    scope._kwargs = kwargs
+
+    # Handle tool calls
+    if scope._kwargs.get("tools"):
+        scope._tools = response_dict.get("choices", [{}])[0].get("message", {}).get("tool_calls")
+    else:
+        scope._tools = None
+
+    common_chat_logic(scope, pricing_info, environment, application_name, metrics,
+        capture_message_content, disable_metrics, version, is_stream=False)
+
+    return response
+
+def process_embedding_response(response, request_model, pricing_info, server_port, server_address,
+    environment, application_name, metrics, start_time, span, capture_message_content=False,
+    disable_metrics=False, version="1.0.0", **kwargs):
+    """
+    Process embedding request and generate Telemetry
+    """
+
+    # Create scope object
+    scope = type("GenericScope", (), {})()
+    response_dict = response_as_dict(response)
+
+    scope._start_time = start_time
+    scope._end_time = time.time()
+    scope._span = span
+    scope._input_tokens = response_dict.get('usage', {}).get('prompt_tokens', 0)
+    scope._response_model = response_dict.get('model')
+    scope._server_address, scope._server_port = server_address, server_port
+    scope._kwargs = kwargs
+
+    # Calculate cost of the operation
+    cost = get_embed_model_cost(request_model, pricing_info, scope._input_tokens)
+
+    # Common Span Attributes
+    common_span_attributes(scope,
+        SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING, SemanticConvention.GEN_AI_SYSTEM_LITELLM,
+        scope._server_address, scope._server_port, request_model, scope._response_model,
+        environment, application_name, False, 0, scope._end_time - scope._start_time, version)
+
+    # Span Attributes for Request parameters
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_ENCODING_FORMATS, [scope._kwargs.get('encoding_format', 'float')])
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_USER, scope._kwargs.get('user', ''))
+
+    # Span Attributes for Cost and Tokens
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_INPUT_TOKENS, scope._input_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_CLIENT_TOKEN_USAGE, scope._input_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_COST, cost)
+
+    # Span Attributes for Content
+    if capture_message_content:
+        scope._span.set_attribute(SemanticConvention.GEN_AI_CONTENT_PROMPT, str(scope._kwargs.get('input', '')))
+
+        # To be removed once the change to span_attributes (from span events) is complete
+        scope._span.add_event(
+            name=SemanticConvention.GEN_AI_CONTENT_PROMPT_EVENT,
+            attributes={
+                SemanticConvention.GEN_AI_CONTENT_PROMPT: str(scope._kwargs.get('input', '')),
+            },
+        )
+
+    scope._span.set_status(Status(StatusCode.OK))
+
+    # Metrics
+    if not disable_metrics:
+        record_embedding_metrics(metrics, SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING, SemanticConvention.GEN_AI_SYSTEM_LITELLM,
+            scope._server_address, scope._server_port, request_model, scope._response_model, environment,
+            application_name, scope._start_time, scope._end_time, scope._input_tokens, cost)
+
+    return response

openlit/semcov/__init__.py

@@ -166,6 +166,7 @@ class SemanticConvention:
     GEN_AI_CONTENT_COMPLETION_EVENT = "gen_ai.content.completion"
     GEN_AI_CONTENT_COMPLETION = "gen_ai.completion"
     GEN_AI_CONTENT_REVISED_PROMPT = "gen_ai.content.revised_prompt"
+    GEN_AI_CONTENT_REASONING = "gen_ai.content.reasoning"
 
     # GenAI Rag
     GEN_AI_RAG_MAX_SEGMENTS = "gen_ai.rag.max_segments"

{openlit-1.34.14.dist-info → openlit-1.34.16.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: openlit
-Version: 1.34.14
+Version: 1.34.16
 Summary: OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications and GPUs, facilitating the integration of observability into your GenAI-driven projects
 License: Apache-2.0
 Keywords: OpenTelemetry,otel,otlp,llm,tracing,openai,anthropic,claude,cohere,llm monitoring,observability,monitoring,gpt,Generative AI,chatGPT,gpu

{openlit-1.34.14.dist-info → openlit-1.34.16.dist-info}/RECORD

@@ -29,10 +29,10 @@ openlit/instrumentation/astra/__init__.py,sha256=-JG3_YHQQaOQUr4XtFzqfaYiQKqviAA
 openlit/instrumentation/astra/astra.py,sha256=L_Yw980eEY0AzMqhNreKamlSplTlL8XiG5lx9Sj3D0c,1610
 openlit/instrumentation/astra/async_astra.py,sha256=87QFKnEQPHywuqMH0dOlnXZ2GqdYDZQgT4TfXB16fPI,1628
 openlit/instrumentation/astra/utils.py,sha256=qBNpugK0R6wQLFx39ZANY1fQvNAIc5PrpEazz-K69Yw,4976
-openlit/instrumentation/azure_ai_inference/__init__.py,sha256=ZoMAX_MUNCNMJqLZgl0A_kQ_lsgoz3VddkHiDT3pVF8,2032
-openlit/instrumentation/azure_ai_inference/async_azure_ai_inference.py,sha256=bRH9iJ9fE6RWibffWw6UfLHs2IhIUdcY3opyvPnQTHg,5058
-openlit/instrumentation/azure_ai_inference/azure_ai_inference.py,sha256=u--3wNMoVRa5pRdMys8osbsCubPESPJw70hdBzAA_tQ,4972
-openlit/instrumentation/azure_ai_inference/utils.py,sha256=JbIsmmi1Xw_gXLjPkhDkdTEJ4Bq8jVs3H4lmXE8Sxhs,11036
+openlit/instrumentation/azure_ai_inference/__init__.py,sha256=_GuYy4ypF6_HICpAC8dNQ5-FBjkcNzPTPF4q3fTM10Q,2512
+openlit/instrumentation/azure_ai_inference/async_azure_ai_inference.py,sha256=SFrniRWPqVBxFJVOpC8w1qNGSYZhCFXeKHVHu5pEdZI,5906
+openlit/instrumentation/azure_ai_inference/azure_ai_inference.py,sha256=hRFuuvaXflctNNbk7N2GOfKaC_eCHbrBWf9_1sZcaGY,5808
+openlit/instrumentation/azure_ai_inference/utils.py,sha256=JqKZgb6VppDbAQ2RdH_dQ2oWVnaqGIA1PCmMl1yrMtA,15491
 openlit/instrumentation/bedrock/__init__.py,sha256=Sfd0vm4Dfm1t-N7vBPRwU57GLTlZP2M4rVYRek_JHXY,1625
 openlit/instrumentation/bedrock/bedrock.py,sha256=kP9ESKzqhWu-dIWseyaeyendUyo6b7xJwjGo3LGi5Jc,2817
 openlit/instrumentation/bedrock/utils.py,sha256=_mTUIbioEg4jfoxocUbfc7RgGjhm9ACelbxIoFu4jbM,11636
@@ -80,9 +80,10 @@ openlit/instrumentation/langchain/async_langchain.py,sha256=rdk3INGcsxsfzZcoJo0y
 openlit/instrumentation/langchain/langchain.py,sha256=zgfzfOIDsaRoVgWl1T4XX2CLO7ttGOD15TagZtYQ-vE,17012
 openlit/instrumentation/letta/__init__.py,sha256=K8PtRKxuueyqEYE3LzxWJ74IieNKSI6dmk9sNRd8Mt0,3031
 openlit/instrumentation/letta/letta.py,sha256=SCIpJ4tdB1l1BmeQx4raaTS4MQO5X15pLvS4PepEKBE,8481
-openlit/instrumentation/litellm/__init__.py,sha256=qRqfwDMhP5adKGI2vRaelAkN12i0e8jtJrT31VFFM5A,2374
-openlit/instrumentation/litellm/async_litellm.py,sha256=DUUOmkyDAxwgET4euyLTjaYxgWGdg_aMyFGbH__qg1A,30502
-openlit/instrumentation/litellm/litellm.py,sha256=xQSqC1HZu7IUVnFAyD442rC6DdO6TSOV9hUTpyPSKW4,30408
+openlit/instrumentation/litellm/__init__.py,sha256=D47yfDLLEKpkaRAy7_Yif70kj88AGqLQYZAABpTN4sE,2284
+openlit/instrumentation/litellm/async_litellm.py,sha256=6cL_hv9t4tuXkcKZvpTdnb0wGTs54lSwGWCtdYZvyXg,6768
+openlit/instrumentation/litellm/litellm.py,sha256=xLna3I_jcywTtIs1tBjHAQKyKjNM07T8GHX9pIqZcQ0,6664
+openlit/instrumentation/litellm/utils.py,sha256=VMSnYkKn9yZtOphIh2ENNuqJtGjz1fXEYUKi5JGHC7A,13195
 openlit/instrumentation/llamaindex/__init__.py,sha256=2pmd9BKw3ab0OJ4yuJEg0-Jkn_haDbXvbUm5r2-rOCU,2007
 openlit/instrumentation/llamaindex/llamaindex.py,sha256=mdT2TvEWD0D9cEkFjXMeTculNoMWkuJ4mj7QWFnvcqY,4085
 openlit/instrumentation/mem0/__init__.py,sha256=IadP3bKgz2HCbnrh9S7AW24uDauGkzsIWeOQaGkOCc4,2447
@@ -137,8 +138,8 @@ openlit/instrumentation/vllm/vllm.py,sha256=VzazF2f4LLwjZDO_G8lIN_d622oSJM0fIO9w
 openlit/otel/events.py,sha256=VrMjTpvnLtYRBHCiFwJojTQqqNpRCxoD4yJYeQrtPsk,3560
 openlit/otel/metrics.py,sha256=GM2PDloBGRhBTkHHkYaqmOwIAQkY124ZhW4sEqW1Fgk,7086
 openlit/otel/tracing.py,sha256=tjV2bEbEDPUB1Z46gE-UsJsb04sRdFrfbhIDkxViZc0,3103
-openlit/semcov/__init__.py,sha256=ptyo37PY-FHDx_PShEvbdns71cD4YvvXw15bCRXKCKM,13461
-openlit-1.34.14.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-openlit-1.34.14.dist-info/METADATA,sha256=qaOh__y9R5tT0z7qveai1LH4KWY7ampN3PzVhhm7D0M,23470
-openlit-1.34.14.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-openlit-1.34.14.dist-info/RECORD,,
+openlit/semcov/__init__.py,sha256=8oIh2VC667NDh8FA3M-ESusHmeus1sgDUD8binx_nAc,13519
+openlit-1.34.16.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+openlit-1.34.16.dist-info/METADATA,sha256=mdKEEE4FgRuUOe_Pl1Crh0S89-A8wCrBchSFJ7cqBRI,23470
+openlit-1.34.16.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+openlit-1.34.16.dist-info/RECORD,,