openlit 1.34.11__tar.gz → 1.34.13__tar.gz

{openlit-1.34.11 → openlit-1.34.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: openlit
-Version: 1.34.11
+Version: 1.34.13
 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-1.34.11 → openlit-1.34.13}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "openlit"
-version = "1.34.11"
+version = "1.34.13"
 description = "OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications and GPUs, facilitating the integration of observability into your GenAI-driven projects"
 authors = ["OpenLIT"]
 license = "Apache-2.0"

{openlit-1.34.11 → openlit-1.34.13}/src/openlit/__helpers.py

@@ -346,12 +346,12 @@ def common_span_attributes(scope, gen_ai_operation, gen_ai_system, server_addres
     scope._span.set_attribute(SemanticConvention.SERVER_ADDRESS, server_address)
     scope._span.set_attribute(SemanticConvention.SERVER_PORT, server_port)
     scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_MODEL, request_model)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_MODEL, scope._response_model)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_MODEL, response_model)
     scope._span.set_attribute(DEPLOYMENT_ENVIRONMENT, environment)
     scope._span.set_attribute(SERVICE_NAME, application_name)
     scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_IS_STREAM, is_stream)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TBT, scope._tbt)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TTFT, scope._ttft)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TBT, tbt)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TTFT, ttft)
     scope._span.set_attribute(SemanticConvention.GEN_AI_SDK_VERSION, version)
 
 def record_completion_metrics(metrics, gen_ai_operation, gen_ai_system, server_address, server_port,

{openlit-1.34.11 → openlit-1.34.13}/src/openlit/instrumentation/ai21/__init__.py

@@ -1,4 +1,3 @@
-# pylint: disable=useless-return, bad-staticmethod-argument, disable=duplicate-code
 """Initializer of Auto Instrumentation of AI21 Functions"""
 
 from typing import Collection
@@ -33,34 +32,37 @@ class AI21Instrumentor(BaseInstrumentor):
         disable_metrics = kwargs.get("disable_metrics")
         version = importlib.metadata.version("ai21")
 
-        #sync
+        # Chat completions
         wrap_function_wrapper(
             "ai21.clients.studio.resources.chat.chat_completions",
             "ChatCompletions.create",
             chat(version, environment, application_name,
-                  tracer, pricing_info, capture_message_content, metrics, disable_metrics),
+                 tracer, pricing_info, capture_message_content, metrics, disable_metrics),
         )
+
+        # RAG completions
         wrap_function_wrapper(
             "ai21.clients.studio.resources.studio_conversational_rag",
             "StudioConversationalRag.create",
             chat_rag(version, environment, application_name,
-                  tracer, pricing_info, capture_message_content, metrics, disable_metrics),
+                     tracer, pricing_info, capture_message_content, metrics, disable_metrics),
         )
 
-        #Async
+        # Async chat completions
         wrap_function_wrapper(
             "ai21.clients.studio.resources.chat.async_chat_completions",
             "AsyncChatCompletions.create",
             async_chat(version, environment, application_name,
-                  tracer, pricing_info, capture_message_content, metrics, disable_metrics),
+                       tracer, pricing_info, capture_message_content, metrics, disable_metrics),
         )
+
+        # Async RAG completions
         wrap_function_wrapper(
             "ai21.clients.studio.resources.studio_conversational_rag",
             "AsyncStudioConversationalRag.create",
             async_chat_rag(version, environment, application_name,
-                  tracer, pricing_info, capture_message_content, metrics, disable_metrics),
+                           tracer, pricing_info, capture_message_content, metrics, disable_metrics),
         )
 
     def _uninstrument(self, **kwargs):
-        # Proper uninstrumentation logic to revert patched methods
         pass

{openlit-1.34.11 → openlit-1.34.13}/src/openlit/instrumentation/ai21/ai21.py

@@ -1,8 +1,7 @@
 """
-Module for monitoring AI21 calls.
+Module for monitoring AI21 API calls.
 """
 
-import logging
 import time
 from opentelemetry.trace import SpanKind
 from openlit.__helpers import (
@@ -15,14 +14,10 @@ from openlit.instrumentation.ai21.utils import (
     process_streaming_chat_response,
     process_chat_rag_response
 )
-
 from openlit.semcov import SemanticConvention
 
-# Initialize logger for logging potential issues and operations
-logger = logging.getLogger(__name__)
-
-def chat(version, environment, application_name,
-                     tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+def chat(version, environment, application_name, tracer, pricing_info,
+    capture_message_content, metrics, disable_metrics):
     """
     Generates a telemetry wrapper for GenAI function call
     """
@@ -45,14 +40,12 @@ def chat(version, environment, application_name,
             self.__wrapped__ = wrapped
             self._span = span
             self._span_name = span_name
-            # Placeholder for aggregating streaming response
             self._llmresponse = ""
             self._response_id = ""
             self._finish_reason = ""
+            self._tools = None
             self._input_tokens = 0
             self._output_tokens = 0
-            self._choices = []
-
             self._args = args
             self._kwargs = kwargs
             self._start_time = time.time()
@@ -83,9 +76,8 @@ def chat(version, environment, application_name,
                 process_chunk(self, chunk)
                 return chunk
             except StopIteration:
-                # Handling exception ensure observability without disrupting operation
                 try:
-                    with tracer.start_as_current_span(self._span_name, kind= SpanKind.CLIENT) as self._span:
+                    with tracer.start_as_current_span(self._span_name, kind=SpanKind.CLIENT) as self._span:
                         process_streaming_chat_response(
                             self,
                             pricing_info=pricing_info,
@@ -96,34 +88,31 @@ def chat(version, environment, application_name,
                             disable_metrics=disable_metrics,
                             version=version
                         )
+
                 except Exception as e:
                     handle_exception(self._span, e)
-                    logger.error("Error in trace creation: %s", e)
+
                 raise
 
     def wrapper(wrapped, instance, args, kwargs):
         """
         Wraps the GenAI function call.
         """
-
         # Check if streaming is enabled for the API call
         streaming = kwargs.get("stream", False)
-
         server_address, server_port = set_server_address_and_port(instance, "api.ai21.com", 443)
         request_model = kwargs.get("model", "jamba-1.5-mini")
 
         span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
 
-        # pylint: disable=no-else-return
         if streaming:
-            # Special handling for streaming response to accommodate the nature of data flow
+            # Special handling for streaming response
             awaited_wrapped = wrapped(*args, **kwargs)
             span = tracer.start_span(span_name, kind=SpanKind.CLIENT)
             return TracedSyncStream(awaited_wrapped, span, span_name, kwargs, server_address, server_port)
-
-        # Handling for non-streaming responses
         else:
-            with tracer.start_as_current_span(span_name, kind= SpanKind.CLIENT) as span:
+            # Handling for non-streaming responses
+            with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
                 start_time = time.time()
                 response = wrapped(*args, **kwargs)
 
@@ -152,23 +141,22 @@ def chat(version, environment, application_name,
 
     return wrapper
 
-def chat_rag(version, environment, application_name,
-                tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+def chat_rag(version, environment, application_name, tracer, pricing_info,
+    capture_message_content, metrics, disable_metrics):
     """
-    Generates a telemetry wrapper for GenAI function call
+    Generates a telemetry wrapper for GenAI RAG function call
     """
 
     def wrapper(wrapped, instance, args, kwargs):
         """
-        Wraps the GenAI function call.
+        Wraps the GenAI RAG function call.
         """
-
         server_address, server_port = set_server_address_and_port(instance, "api.ai21.com", 443)
         request_model = kwargs.get("model", "jamba-1.5-mini")
 
         span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
 
-        with tracer.start_as_current_span(span_name, kind= SpanKind.CLIENT) as span:
+        with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
             start_time = time.time()
             response = wrapped(*args, **kwargs)
 

{openlit-1.34.11 → openlit-1.34.13}/src/openlit/instrumentation/ai21/async_ai21.py

@@ -1,8 +1,7 @@
 """
-Module for monitoring AI21 calls.
+Module for monitoring AI21 API calls (async version).
 """
 
-import logging
 import time
 from opentelemetry.trace import SpanKind
 from openlit.__helpers import (
@@ -15,21 +14,17 @@ from openlit.instrumentation.ai21.utils import (
     process_streaming_chat_response,
     process_chat_rag_response
 )
-
 from openlit.semcov import SemanticConvention
 
-# Initialize logger for logging potential issues and operations
-logger = logging.getLogger(__name__)
-
-def async_chat(version, environment, application_name,
-                     tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+def async_chat(version, environment, application_name, tracer, pricing_info,
+    capture_message_content, metrics, disable_metrics):
     """
     Generates a telemetry wrapper for GenAI function call
     """
 
     class TracedAsyncStream:
         """
-        Wrapper for streaming responses to collect telemetry.
+        Wrapper for async streaming responses to collect telemetry.
         """
 
         def __init__(
@@ -45,14 +40,12 @@ def async_chat(version, environment, application_name,
             self.__wrapped__ = wrapped
             self._span = span
             self._span_name = span_name
-            # Placeholder for aggregating streaming response
             self._llmresponse = ""
             self._response_id = ""
             self._finish_reason = ""
+            self._tools = None
             self._input_tokens = 0
             self._output_tokens = 0
-            self._choices = []
-
             self._args = args
             self._kwargs = kwargs
             self._start_time = time.time()
@@ -83,9 +76,8 @@ def async_chat(version, environment, application_name,
                 process_chunk(self, chunk)
                 return chunk
             except StopAsyncIteration:
-                # Handling exception ensure observability without disrupting operation
                 try:
-                    with tracer.start_as_current_span(self._span_name, kind= SpanKind.CLIENT) as self._span:
+                    with tracer.start_as_current_span(self._span_name, kind=SpanKind.CLIENT) as self._span:
                         process_streaming_chat_response(
                             self,
                             pricing_info=pricing_info,
@@ -96,6 +88,7 @@ def async_chat(version, environment, application_name,
                             disable_metrics=disable_metrics,
                             version=version
                         )
+
                 except Exception as e:
                     handle_exception(self._span, e)
 
@@ -105,25 +98,21 @@ def async_chat(version, environment, application_name,
         """
         Wraps the GenAI function call.
         """
-
         # Check if streaming is enabled for the API call
         streaming = kwargs.get("stream", False)
-
         server_address, server_port = set_server_address_and_port(instance, "api.ai21.com", 443)
         request_model = kwargs.get("model", "jamba-1.5-mini")
 
         span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
 
-        # pylint: disable=no-else-return
         if streaming:
-            # Special handling for streaming response to accommodate the nature of data flow
+            # Special handling for streaming response
             awaited_wrapped = await wrapped(*args, **kwargs)
             span = tracer.start_span(span_name, kind=SpanKind.CLIENT)
             return TracedAsyncStream(awaited_wrapped, span, span_name, kwargs, server_address, server_port)
-
-        # Handling for non-streaming responses
         else:
-            with tracer.start_as_current_span(span_name, kind= SpanKind.CLIENT) as span:
+            # Handling for non-streaming responses
+            with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
                 start_time = time.time()
                 response = await wrapped(*args, **kwargs)
 
@@ -152,23 +141,22 @@ def async_chat(version, environment, application_name,
 
     return wrapper
 
-def async_chat_rag(version, environment, application_name,
-                tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+def async_chat_rag(version, environment, application_name, tracer, pricing_info,
+    capture_message_content, metrics, disable_metrics):
     """
-    Generates a telemetry wrapper for GenAI function call
+    Generates a telemetry wrapper for GenAI RAG function call
     """
 
     async def wrapper(wrapped, instance, args, kwargs):
         """
-        Wraps the GenAI function call.
+        Wraps the GenAI RAG function call.
         """
-
         server_address, server_port = set_server_address_and_port(instance, "api.ai21.com", 443)
         request_model = kwargs.get("model", "jamba-1.5-mini")
 
         span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
 
-        with tracer.start_as_current_span(span_name, kind= SpanKind.CLIENT) as span:
+        with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
             start_time = time.time()
             response = await wrapped(*args, **kwargs)
 

openlit-1.34.13/src/openlit/instrumentation/ai21/utils.py

@@ -0,0 +1,317 @@
+"""
+AI21 OpenTelemetry instrumentation utility functions
+"""
+
+import time
+
+from opentelemetry.trace import Status, StatusCode
+
+from openlit.__helpers import (
+    calculate_ttft,
+    response_as_dict,
+    calculate_tbt,
+    general_tokens,
+    get_chat_model_cost,
+    common_span_attributes,
+    record_completion_metrics,
+)
+from openlit.semcov import SemanticConvention
+
+def format_content(messages):
+    """
+    Process a list of messages to extract content.
+    """
+
+    formatted_messages = []
+    for message in messages:
+        # Handle different message formats
+        if hasattr(message, "role") and (hasattr(message, "content") or hasattr(message, "text")):
+            # ChatMessage object (AI21 format)
+            role = str(message.role) if hasattr(message.role, 'value') else str(message.role)
+            content = getattr(message, "content", None) or getattr(message, "text", "")
+        elif isinstance(message, dict):
+            # Dictionary format
+            role = message["role"]
+            content = message["content"]
+        else:
+            # Fallback - try to extract as string
+            role = str(getattr(message, "role", "unknown"))
+            content = str(getattr(message, "content", "") or getattr(message, "text", ""))
+
+        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
+
+    if chunked.get("usage"):
+        scope._input_tokens = chunked.get("usage").get("prompt_tokens")
+        scope._output_tokens = chunked.get("usage").get("completion_tokens")
+        scope._response_id = chunked.get("id")
+        scope._finish_reason = chunked.get("choices", [{}])[0].get("finish_reason")
+        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", "jamba-1.5-mini")
+
+    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_AI21,
+        scope._server_address, scope._server_port, request_model, request_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", 0.4))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TOP_P, scope._kwargs.get("top_p", 1.0))
+
+    # 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_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
+    if scope._tools:
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_NAME, scope._tools.get("function", {}).get("name", ""))
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_CALL_ID, str(scope._tools.get("id", "")))
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_ARGS, str(scope._tools.get("function", {}).get("arguments", "")))
+
+    # 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_AI21,
+            scope._server_address, scope._server_port, request_model, request_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._response_id = response_dict.get("id")
+    scope._input_tokens = response_dict.get("usage", {}).get("prompt_tokens", 0)
+    scope._output_tokens = response_dict.get("usage", {}).get("completion_tokens", 0)
+    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
+    scope._finish_reason = str(response_dict.get("choices", [])[0].get("finish_reason", ""))
+
+    # 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 common_chat_rag_logic(scope, pricing_info, environment, application_name, metrics,
+    capture_message_content, disable_metrics, version):
+    """
+    Process RAG chat request and generate Telemetry
+    """
+
+    prompt = format_content(scope._kwargs.get("messages", []))
+    request_model = scope._kwargs.get("model", "jamba-1.5-mini")
+
+    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_AI21,
+        scope._server_address, scope._server_port, request_model, scope._response_model,
+        environment, application_name, False, scope._tbt, scope._ttft, version)
+
+    # RAG-specific span attributes
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RAG_MAX_SEGMENTS, scope._kwargs.get("max_segments", -1))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RAG_STRATEGY, scope._kwargs.get("retrieval_strategy", "segments"))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RAG_MAX_NEIGHBORS, scope._kwargs.get("max_neighbors", -1))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RAG_FILE_IDS, str(scope._kwargs.get("file_ids", "")))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RAG_DOCUMENTS_PATH, scope._kwargs.get("path", ""))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RAG_SIMILARITY_THRESHOLD,
+                                scope._kwargs.get("retrieval_similarity_threshold", -1))
+
+    # Standard span attributes
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_ID, scope._response_id)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_OUTPUT_TYPE, "text" if isinstance(scope._llmresponse, str) else "json")
+    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)
+
+    # Handle tool calls
+    if scope._kwargs.get("tools"):
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_CALLS,
+            str(scope._choices[0].get("message", {}).get("tool_calls", "")))
+
+    # Content attributes
+    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_AI21,
+            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_chat_rag_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 RAG 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
+
+    # Format input messages and calculate input tokens
+    prompt = format_content(kwargs.get("messages", []))
+    input_tokens = general_tokens(prompt)
+
+    # Process response choices
+    choices = response_dict.get("choices", [])
+    aggregated_completion = []
+    output_tokens = 0
+
+    for i in range(kwargs.get("n", 1)):
+        content = choices[i].get("content", "")
+        aggregated_completion.append(content)
+        output_tokens += general_tokens(content)
+
+    scope._llmresponse = "".join(aggregated_completion)
+    scope._response_id = response_dict.get("id", "")
+    scope._response_model = request_model
+    scope._input_tokens = input_tokens
+    scope._output_tokens = output_tokens
+    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
+    scope._finish_reason = ""
+    scope._tools = None
+    scope._choices = choices
+
+    common_chat_rag_logic(scope, pricing_info, environment, application_name, metrics,
+        capture_message_content, disable_metrics, version)
+
+    return response