Updated changelog

.github/workflows/documentation_codeblock_tests.yml

@@ -24,20 +24,20 @@ jobs:
           # Get list of changed files in docs directory
           if [[ "${{ github.event_name }}" == "pull_request" ]]; then
             # For pull requests, compare with base branch
-            echo "paths=$(
-              git diff --name-only origin/${{ github.base_ref }} |
-              grep -E '^apps/opik-documentation/documentation/docs/.*\.(md|mdx)$' |
-              sed 's|apps/opik-documentation/documentation/||' |
-              jq -R -s -c 'split("\n")[:-1]'
-            )" >> $GITHUB_OUTPUT
+            CHANGED_FILES=$(git diff --name-only origin/${{ github.base_ref }} | grep -E '^apps/opik-documentation/documentation/fern/docs/.*\.(md|mdx)$' || true)
+            if [ -n "$CHANGED_FILES" ]; then
+              echo "paths=$(echo "$CHANGED_FILES" | sed 's|apps/opik-documentation/documentation/||' | jq -R -s 'split("\n")[:-1]' -c)" >> $GITHUB_OUTPUT
+            else
+              echo "paths=[]" >> $GITHUB_OUTPUT
+            fi
           else
-            # For manual runs and scheduled runs, check all files
-            echo "paths=$(
-              (
-                ls -d docs/*/ 2>/dev/null;
-                find docs -maxdepth 1 -type f -name "*.md" -o -name "*.mdx"
-              ) | jq -R -s -c 'split("\n")[:-1]'
-            )" >> $GITHUB_OUTPUT
+            # For manual runs, get all md/mdx files
+            FILES=$(find fern/docs -type f \( -name "*.md" -o -name "*.mdx" \))
+            if [ -n "$FILES" ]; then
+              echo "paths=$(echo "$FILES" | jq -R -s 'split("\n")[:-1]' -c)" >> $GITHUB_OUTPUT
+            else
+              echo "paths=[]" >> $GITHUB_OUTPUT
+            fi
           fi
 
   test:

apps/opik-documentation/documentation/docs/cookbook/instructor.ipynb

@@ -26,7 +26,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet opik instructor"
+    "%pip install --upgrade --quiet opik instructor anthropic google-generativeai google-genai"
    ]
   },
   {

apps/opik-documentation/documentation/fern/docs.yml

@@ -78,6 +78,9 @@ navigation:
           - page: Log traces
             path: docs/tracing/log_traces.mdx
             slug: log_traces
+          - page: Log conversations
+            path: docs/tracing/log_chat_conversations.mdx
+            slug: log_chat_conversations
           - page: Log agents
             path: docs/tracing/log_agents.mdx
             slug: log_agents

apps/opik-documentation/documentation/fern/docs/changelog/2025-03-03.mdx

@@ -0,0 +1,18 @@
+**Opik Dashboard**:
+
+- Chat conversations can now be reviewed in the platform
+
+<Frame>
+  <img src="/img/changelog/2025-03-03/chat_conversations.png" />
+</Frame>
+
+- Added the ability to leave comments on experiments
+- You can now leave reasons on feedback scores, see [Annotating Traces](/tracing/annotate_traces)
+- Added support for Gemini in the playground
+- A thumbs up / down feedback score definition is now added to all projects by default to make it easier
+  to annotate traces.
+
+**JS / TS SDK**:
+
+- The AnswerRelevanceMetric can now be run without providing a context field
+- Made some updates to how metrics are uploaded to optimize data ingestion

apps/opik-documentation/documentation/fern/docs/cookbook/anthropic.mdx

@@ -46,7 +46,9 @@ import os
 from opik.integrations.anthropic import track_anthropic
 
 anthropic_client = anthropic.Anthropic()
-anthropic_client = track_anthropic(anthropic_client, project_name="anthropic-integration-demo")
+anthropic_client = track_anthropic(
+    anthropic_client, project_name="anthropic-integration-demo"
+)
 ```
 
 

apps/opik-documentation/documentation/fern/docs/cookbook/gemini.mdx

@@ -10,7 +10,7 @@ Opik integrates with Gemini to provide a simple way to log traces for all Gemini
 
 
 ```python
-%pip install --upgrade opik google-generativeai litellm
+%pip install --upgrade opik google-genai litellm
 ```
 
 
@@ -28,45 +28,34 @@ First, we will set up our OpenAI API keys.
 ```python
 import os
 import getpass
-import google.generativeai as genai
 
-if "GEMINI_API_KEY" not in os.environ:
-    genai.configure(api_key=getpass.getpass("Enter your Gemini API key: "))
+if "GOOGLE_API_KEY" not in os.environ:
+    os.environ["GOOGLE_API_KEY"] = getpass.getpass("Enter your Gemini API key: ")
 ```
 
-## Configure LiteLLM
+## Logging traces
 
-Add the LiteLLM OpikTracker to log traces and steps to Opik:
+Now each completion will logs a separate trace to LiteLLM:
 
 
 ```python
-import litellm
-import os
-from litellm.integrations.opik.opik import OpikLogger
+from google import genai
 from opik import track
-from opik.opik_context import get_current_span_data
+from opik.integrations.genai import track_genai
 
 os.environ["OPIK_PROJECT_NAME"] = "gemini-integration-demo"
-opik_logger = OpikLogger()
-litellm.callbacks = [opik_logger]
-```
-
-## Logging traces
-
-Now each completion will logs a separate trace to LiteLLM:
 
+client = genai.Client()
+gemini_client = track_genai(client)
 
-```python
 prompt = """
 Write a short two sentence story about Opik.
 """
 
-response = litellm.completion(
-    model="gemini/gemini-pro",
-    messages=[{"role": "user", "content": prompt}],
+response = gemini_client.models.generate_content(
+    model="gemini-2.0-flash-001", contents=prompt
 )
-
-print(response.choices[0].message.content)
+print(response.text)
 ```
 
 The prompt and response messages are automatically logged to Opik and can be viewed in the UI.
@@ -81,31 +70,19 @@ If you have multiple steps in your LLM pipeline, you can use the `track` decorat
 ```python
 @track
 def generate_story(prompt):
-    response = litellm.completion(
-        model="gemini/gemini-pro",
-        messages=[{"role": "user", "content": prompt}],
-        metadata={
-            "opik": {
-                "current_span_data": get_current_span_data(),
-            },
-        },
+    response = gemini_client.models.generate_content(
+        model="gemini-2.0-flash-001", contents=prompt
     )
-    return response.choices[0].message.content
+    return response.text
 
 
 @track
 def generate_topic():
     prompt = "Generate a topic for a story about Opik."
-    response = litellm.completion(
-        model="gemini/gemini-pro",
-        messages=[{"role": "user", "content": prompt}],
-        metadata={
-            "opik": {
-                "current_span_data": get_current_span_data(),
-            },
-        },
+    response = gemini_client.models.generate_content(
+        model="gemini-2.0-flash-001", contents=prompt
     )
-    return response.choices[0].message.content
+    return response.text
 
 
 @track
@@ -121,5 +98,3 @@ generate_opik_story()
 The trace can now be viewed in the UI:
 
 ![Gemini Cookbook](https://raw.githubusercontent.com/comet-ml/opik/main/apps/opik-documentation/documentation/fern/img/cookbook/gemini_trace_decorator_cookbook.png)
-
-

apps/opik-documentation/documentation/fern/docs/cookbook/instructor.mdx

@@ -10,7 +10,7 @@
 
 
 ```python
-%pip install --upgrade --quiet opik instructor
+%pip install --upgrade --quiet opik instructor anthropic google-generativeai google-genai
 ```
 
 

apps/opik-documentation/documentation/fern/docs/cookbook/quickstart_notebook.mdx

@@ -433,8 +433,6 @@ We can now use the `evaluate` method to evaluate the summaries in our dataset:
 ```python
 from opik.evaluation import evaluate
 
-os.environ["OPIK_PROJECT_NAME"] = "summary-evaluation-prompts"
-
 MODEL = "gpt-4o-mini"
 DENSITY_ITERATIONS = 2
 
@@ -490,8 +488,6 @@ Guidelines:
 ```python
 from opik.evaluation import evaluate
 
-os.environ["OPIK_PROJECT_NAME"] = "summary-evaluation-prompts"
-
 MODEL = "gpt-4o-mini"
 DENSITY_ITERATIONS = 2
 

apps/opik-documentation/documentation/fern/docs/tracing/annotate_traces.mdx

@@ -1,4 +1,5 @@
-Annotating traces is a crucial aspect of evaluating and improving your LLM-based applications. By systematically recording qualitative or quantitative feedback on specific interactions or entire conversation flows, you can:
+Annotating traces is a crucial aspect of evaluating and improving your LLM-based applications. By systematically recording qualitative or quantitative
+feedback on specific interactions or entire conversation flows, you can:
 
 1. Track performance over time
 2. Identify areas for improvement
@@ -10,7 +11,8 @@ Opik allows you to annotate traces through the SDK or the UI.
 
 ## Annotating Traces through the UI
 
-To annotate traces through the UI, you can navigate to the trace you want to annotate in the traces page and click on the `Annotate` button. This will open a sidebar where you can add annotations to the trace.
+To annotate traces through the UI, you can navigate to the trace you want to annotate in the traces page and click on the `Annotate` button.
+This will open a sidebar where you can add annotations to the trace.
 
 You can annotate both traces and spans through the UI, make sure you have selected the correct span in the sidebar.
 
@@ -19,10 +21,12 @@ You can annotate both traces and spans through the UI, make sure you have select
 </Frame>
 
 <Tip>
-  In order to ensure a consistent set of feedback, you will need to define feedback definitions in the `Feedback
-  Definitions` page which supports both numerical and categorical annotations.
+  Once a feedback scores has been provided, you can also add a reason to explain why this particular score was provided.
+  This is useful to add additional context to the score.
 </Tip>
 
+You can also add comments to traces and experiments to share insights with other team members.
+
 ## Online evaluation
 
 You don't need to manually annotate each trace to measure the performance of your LLM applications! By using Opik's [online evaluation feature](/production/rules), you can define LLM as a Judge metrics that will automatically score all, or a subset, of your production traces.
@@ -77,9 +81,10 @@ client.log_spans_feedback_scores(
 )
 ```
 
-:::note
-The `FeedbackScoreDict` class supports an optional `reason` field that can be used to provide a human-readable explanation for the feedback score.
-:::
+<Note>
+  The `FeedbackScoreDict` class supports an optional `reason` field that can be used to provide a human-readable
+  explanation for the feedback score.
+</Note>
 
 ### Using Opik's built-in evaluation metrics
 
@@ -90,7 +95,7 @@ Opik's built-in evaluation metrics are broken down into two main categories:
 1. Heuristic metrics
 2. LLM as a judge metrics
 
-### Heuristic Metrics
+#### Heuristic Metrics
 
 Heuristic metrics are use rule-based or statistical methods that can be used to evaluate the output of LLM models.
 
@@ -118,7 +123,7 @@ score = metric.score(
 )
 ```
 
-### LLM as a Judge Metrics
+#### LLM as a Judge Metrics
 
 For LLM outputs that cannot be evaluated using heuristic metrics, you can use LLM as a judge metrics. These metrics are based on the idea of using an LLM to evaluate the output of another LLM.
 

apps/opik-documentation/documentation/fern/docs/tracing/log_chat_conversations.mdx

@@ -0,0 +1,78 @@
+You can log chat conversations to the Opik platform and track the full conversations
+your users are having with your chatbot.
+
+<Frame>
+  <img src="/img/tracing/chat_conversations.png" />
+</Frame>
+
+## Logging conversations
+
+You can log chat conversations by specifying the `thread_id` parameter when using either the low level SDK or
+Python decorators:
+
+<Tabs>
+    <Tab title="Python decorators" value="Python decorators">
+    ```python
+    import opik
+    from opik import opik_context
+
+    @opik.track
+    def chat_message(input, thread_id):
+        opik_context.update_current_trace(
+            thread_id=thread_id
+        )
+        return "Opik is an Open Source GenAI platform"
+
+    thread_id = "f174a"
+    chat_message("What is Opik ?", thread_id)
+    chat_message("Repeat the previous message", thread_id)
+    ```
+    </Tab>
+    <Tab title="Low level SDK" value="Low level SDK">
+    ```python
+    import opik
+
+    opik_client = opik.Opik()
+
+    thread_id = "55d84"
+
+    # Log a first message
+    trace = opik_client.trace(
+        name="chat_conversation",
+        input="What is Opik?",
+        output="Opik is an Open Source GenAI platform",
+        thread_id=thread_id
+    )
+
+    # Log a second message
+    trace = opik_client.trace(
+        name="chat_conversation",
+        input="Can you track chat conversations in Opik",
+        output="Yes, of course !",
+        thread_id=thread_id
+    )
+    ```
+    </Tab>
+
+</Tabs>
+
+<Note>
+  The input to each trace will be displayed as the user message while the output will be displayed as the AI assistant
+  response.
+</Note>
+
+## Reviewing conversations
+
+Conversations can be viewed at a project level in the `threads` tab. All conversations are tracked and by clicking on the thread ID you will be able to
+view the full conversation.
+
+The thread view supports markdown making it easier for you to review the content that was returned to the user. If you would like to dig in deeper, you
+can click on the `View trace` button to deepdive into how the AI assistant response was generated.
+
+By clicking on the thumbs up or thumbs down icons, you can quickly rate the AI assistant response. This feedback score will be logged and associated to
+the relevant trace. By switching to the trace view, you can review the full trace as well as add additional feedback scores through the annotation
+functionality.
+
+<Frame>
+  <img src="/img/tracing/chat_conversations_actions.png" />
+</Frame>