Documentation updates (#356)

* Documentation updates * Fix typo in docs
comet-ml · Oct 7, 2024 · 9d0190a · 9d0190a
1 parent 92f7857
commit 9d0190a
Show file tree

Hide file tree

Showing 14 changed files with 98 additions and 38 deletions.
diff --git a/...opik-documentation/documentation/docs/cookbook/evaluate_hallucination_metric.md b/...opik-documentation/documentation/docs/cookbook/evaluate_hallucination_metric.md
@@ -4,9 +4,9 @@ For this guide we will be evaluating the Hallucination metric included in the LL
 
 ## Creating an account on Comet.com
 
-[Comet](https://www.comet.com/site?from=llm&utm_source=opik&utm_medium=colab&utm_content=eval_hall) provides a hosted version of the Opik platform, [simply create an account](https://www.comet.com/signup?from=llm&utm_source=opik&utm_medium=colab&utm_content=eval_hall) and grab you API Key.
+[Comet](https://www.comet.com/site/?from=llm&utm_source=opik&utm_medium=colab&utm_content=eval_hall&utm_campaign=opik) provides a hosted version of the Opik platform, [simply create an account](https://www.comet.com/signup?from=llm&utm_source=opik&utm_medium=colab&utm_content=eval_hall&utm_campaign=opik) and grab you API Key.
 
-> You can also run the Opik platform locally, see the [installation guide](https://www.comet.com/docs/opik/self-host/overview/?from=llm&utm_source=opik&utm_medium=colab&utm_content=eval_hall) for more information.
+> You can also run the Opik platform locally, see the [installation guide](https://www.comet.com/docs/opik/self-host/overview/?from=llm&utm_source=opik&utm_medium=colab&utm_content=eval_hall&utm_campaign=opik) for more information.
 
 
 ```python

diff --git a/apps/opik-documentation/documentation/docs/cookbook/evaluate_moderation_metric.md b/apps/opik-documentation/documentation/docs/cookbook/evaluate_moderation_metric.md
@@ -4,9 +4,9 @@ For this guide we will be evaluating the Moderation metric included in the LLM E
 
 ## Creating an account on Comet.com
 
-[Comet](https://www.comet.com/site?from=llm&utm_source=opik&utm_medium=colab&utm_content=eval_mod) provides a hosted version of the Opik platform, [simply create an account](https://www.comet.com/signup?from=llm&utm_source=opik&utm_medium=colab&utm_content=eval_mod) and grab you API Key.
+[Comet](https://www.comet.com/site?from=llm&utm_source=opik&utm_medium=colab&utm_content=eval_mod&utm_campaign=opik) provides a hosted version of the Opik platform, [simply create an account](https://www.comet.com/signup/?from=llm&utm_source=opik&utm_medium=colab&utm_content=eval_mod&utm_campaign=opik) and grab you API Key.
 
-> You can also run the Opik platform locally, see the [installation guide](https://www.comet.com/docs/opik/self-host/overview/?from=llm&utm_source=opik&utm_medium=colab&utm_content=eval_mod) for more information.
+> You can also run the Opik platform locally, see the [installation guide](https://www.comet.com/docs/opik/self-host/overview/?from=llm&utm_source=opik&utm_medium=colab&utm_content=eval_mod&utm_campaign=opik) for more information.
 
 
 ```python

diff --git a/apps/opik-documentation/documentation/docs/cookbook/langchain.ipynb b/apps/opik-documentation/documentation/docs/cookbook/langchain.ipynb
@@ -207,7 +207,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Automatting the evaluation\n",
+    "## Automating the evaluation\n",
     "\n",
     "In order to ensure our LLM application is working correctly, we will test it on our synthetic dataset.\n",
     "\n",

diff --git a/apps/opik-documentation/documentation/docs/cookbook/langchain.md b/apps/opik-documentation/documentation/docs/cookbook/langchain.md
@@ -10,9 +10,9 @@ We will highlight three different parts of the workflow:
 
 ## Creating an account on Comet.com
 
-[Comet](https://www.comet.com/site?from=llm&utm_source=opik&utm_medium=colab&utm_content=langchain) provides a hosted version of the Opik platform, [simply create an account](https://www.comet.com/signup?from=llm&utm_source=opik&utm_medium=colab&utm_content=langchain) and grab you API Key.
+[Comet](https://www.comet.com/site?from=llm&utm_source=opik&utm_medium=colab&utm_content=langchain&utm_campaign=opik) provides a hosted version of the Opik platform, [simply create an account](https://www.comet.com/signup?from=llm&utm_source=opik&utm_medium=colab&utm_content=langchain&utm_campaign=opik) and grab you API Key.
 
-> You can also run the Opik platform locally, see the [installation guide](https://www.comet.com/docs/opik/self-host/overview/?from=llm&utm_source=opik&utm_medium=colab&utm_content=langchain) for more information.
+> You can also run the Opik platform locally, see the [installation guide](https://www.comet.com/docs/opik/self-host/overview/?from=llm&utm_source=opik&utm_medium=colab&utm_content=langchain&utm_campaign=opik) for more information.
 
 
 ```python

diff --git a/apps/opik-documentation/documentation/docs/cookbook/llama-index.md b/apps/opik-documentation/documentation/docs/cookbook/llama-index.md
@@ -12,9 +12,9 @@ For this guide we will be downloading the essays from Paul Graham and use them a
 
 ## Creating an account on Comet.com
 
-[Comet](https://www.comet.com/site?from=llm&utm_source=opik&utm_medium=colab&utm_content=llamaindex) provides a hosted version of the Opik platform, [simply create an account](https://www.comet.com/signup?from=llm&utm_source=opik&utm_medium=colab&utm_content=llamaindex) and grab you API Key.
+[Comet](https://www.comet.com/site?from=llm&utm_source=opik&utm_medium=colab&utm_content=llamaindex&utm_campaign=opik) provides a hosted version of the Opik platform, [simply create an account](https://www.comet.com/signup?from=llm&=opik&utm_medium=colab&utm_content=llamaindex&utm_campaign=opik) and grab you API Key.
 
-> You can also run the Opik platform locally, see the [installation guide](https://www.comet.com/docs/opik/self-host/overview/?from=llm&utm_source=opik&utm_medium=colab&utm_content=llamaindex) for more information.
+> You can also run the Opik platform locally, see the [installation guide](https://www.comet.com/docs/opik/self-host/overview/?from=llm&utm_source=opik&utm_medium=colab&utm_content=llamaindex&utm_campaign=opik) for more information.
 
 
 ```python

diff --git a/apps/opik-documentation/documentation/docs/cookbook/openai.md b/apps/opik-documentation/documentation/docs/cookbook/openai.md
@@ -5,9 +5,9 @@ Opik integrates with OpenAI to provide a simple way to log traces for all OpenAI
 
 ## Creating an account on Comet.com
 
-[Comet](https://www.comet.com/site?from=llm&utm_source=opik&utm_medium=colab&utm_content=openai) provides a hosted version of the Opik platform, [simply create an account](https://www.comet.com/signup?from=llm&utm_source=opik&utm_medium=colab&utm_content=openai) and grab you API Key.
+[Comet](https://www.comet.com/site?from=llm&utm_source=opik&utm_medium=colab&utm_content=openai&utm_campaign=opik) provides a hosted version of the Opik platform, [simply create an account](https://www.comet.com/signup?from=llm&utm_source=opik&utm_medium=colab&utm_content=openai&utm_campaign=opik) and grab you API Key.
 
-> You can also run the Opik platform locally, see the [installation guide](https://www.comet.com/docs/opik/self-host/overview/?from=llm&utm_source=opik&utm_medium=colab&utm_content=openai) for more information.
+> You can also run the Opik platform locally, see the [installation guide](https://www.comet.com/docs/opik/self-host/overview/?from=llm&utm_source=opik&utm_medium=colab&utm_content=openai&utm_campaign=opik) for more information.
 
 
 ```python

diff --git a/apps/opik-documentation/documentation/docs/cookbook/ragas.md b/apps/opik-documentation/documentation/docs/cookbook/ragas.md
@@ -9,9 +9,9 @@ There are two main ways to use Opik with Ragas:
 
 ## Creating an account on Comet.com
 
-[Comet](https://www.comet.com/site?from=llm&utm_source=opik&utm_medium=colab&utm_content=openai) provides a hosted version of the Opik platform, [simply create an account](https://www.comet.com/signup?from=llm&utm_source=opik&utm_medium=colab&utm_content=ragas) and grab you API Key.
+[Comet](https://www.comet.com/site?from=llm&utm_source=opik&utm_medium=colab&utm_content=ragas&utm_campaign=opik) provides a hosted version of the Opik platform, [simply create an account](https://www.comet.com/signup?from=llm&utm_source=opik&utm_medium=colab&utm_content=ragas&utm_campaign=opik) and grab you API Key.
 
-> You can also run the Opik platform locally, see the [installation guide](https://www.comet.com/docs/opik/self-host/overview/?from=llm&utm_source=opik&utm_medium=colab&utm_content=ragas) for more information.
+> You can also run the Opik platform locally, see the [installation guide](https://www.comet.com/docs/opik/self-host/overview/?from=llm&utm_source=opik&utm_medium=colab&utm_content=ragas&utm_campaign=opik) for more information.
 
 
 ```python

diff --git a/apps/opik-documentation/documentation/docs/evaluation/metrics/heuristic_metrics.md b/apps/opik-documentation/documentation/docs/evaluation/metrics/heuristic_metrics.md
@@ -25,9 +25,9 @@ You can score an LLM response by first initializing the metrics and then calling
 ```python
 from opik.evaluation.metrics import Contains
 
-metric = Contains("hello", case_sensitive=True)
+metric = Contains(name="contains_hello", case_sensitive=True)
 
-score = metric.score("Hello world !")
+score = metric.score(output="Hello world !", reference="Hello")
 
 print(score)
 ```
@@ -41,12 +41,9 @@ The `Equals` metric can be used to check if the output of an LLM exactly matches
 ```python
 from opik.evaluation.metrics import Equals
 
-metric = Equals(
-    name="checks_equals_hello",
-    searched_value="hello",
-)
+metric = Equals()
 
-score = metric.score("Hello world !")
+score = metric.score(output="Hello world !", reference="Hello, world !")
 print(score)
 ```
 
@@ -57,13 +54,9 @@ The `Contains` metric can be used to check if the output of an LLM contains a sp
 ```python
 from opik.evaluation.metrics import Contains
 
-metric = Contains(
-    name="checks_contains_hello",
-    searched_value="hello",
-    case_sensitive=False,
-)
+metric = Contains(case_sensitive=False)
 
-score = metric.score("Hello world !")
+score = metric.score(output="Hello world !", reference="Hello")
 print(score)
 ```
 
@@ -74,10 +67,7 @@ The `RegexMatch` metric can be used to check if the output of an LLM matches a s
 ```python
 from opik.evaluation.metrics import RegexMatch
 
-metric = RegexMatch(
-    name="checks_regex_match",
-    regex_pattern="^[a-zA-Z0-9]+$",
-)
+metric = RegexMatch(regex="^[a-zA-Z0-9]+$")
 
 score = metric.score("Hello world !")
 print(score)
@@ -92,7 +82,7 @@ from opik.evaluation.metrics import IsJson
 
 metric = IsJson(name="is_json_metric")
 
-score = metric.score('{"key": "some_valid_sql"}')
+score = metric.score(output='{"key": "some_valid_sql"}')
 print(score)
 ```
 
@@ -103,8 +93,8 @@ The `LevenshteinRatio` metric can be used to check if the output of an LLM is va
 ```python
 from opik.evaluation.metrics import LevenshteinRatio
 
-metric = LevenshteinRatio(name="levenshtein_ratio_metric", searched_value="hello")
+metric = LevenshteinRatio()
 
-score = metric.score("Hello world !")
+score = metric.score(output="Hello world !", reference="hello")
 print(score)
 ``` 
diff --git a/apps/opik-documentation/documentation/docs/tracing/annotate_traces.md b/apps/opik-documentation/documentation/docs/tracing/annotate_traces.md
@@ -1,5 +1,5 @@
 ---
-sidebar_position: 3
+sidebar_position: 4
 sidebar_label: Annotate Traces
 ---
 

diff --git a/apps/opik-documentation/documentation/docs/tracing/integrations/_category_.json b/apps/opik-documentation/documentation/docs/tracing/integrations/_category_.json
@@ -1,7 +1,7 @@
 {
     "label": "Integrations",
-    "position": 6,
+    "position": 5,
     "link": {
       "type": "generated-index"
     }
-  }
+  }
diff --git a/apps/opik-documentation/documentation/docs/tracing/log_distributed_traces.md b/apps/opik-documentation/documentation/docs/tracing/log_distributed_traces.md
@@ -1,5 +1,5 @@
 ---
-sidebar_position: 2
+sidebar_position: 3
 sidebar_label: Log Distributed Traces
 ---
 

diff --git a/apps/opik-documentation/documentation/docs/tracing/log_multimodal_traces.md b/apps/opik-documentation/documentation/docs/tracing/log_multimodal_traces.md
@@ -0,0 +1,70 @@
+---
+sidebar_position: 2
+sidebar_label: Log Multimodal Traces
+toc_min_heading_level: 2
+toc_max_heading_level: 4
+---
+
+# Log Multimodal Traces
+
+Opik supports multimodal traces allowing you to track not just the text input and output of your LLM, but also images.
+
+![Traces with OpenAI](/img/tracing/image_trace.png)
+
+## Log a trace with an image using OpenAI SDK
+
+As long as your trace input or output follows the OpenAI format, images will automatically be detected and rendered in the Opik UI.
+
+We recommend that you use the [`track_openai`](/python-sdk-reference/integrations/openai/track_openai.html) wrapper to ensure the OpenAI API call is traced correctly:
+
+```python
+from opik.integrations.openai import track_openai
+from openai import OpenAI
+
+# Create the OpenAI client and enable Opik tracing
+client = track_openai(OpenAI())
+
+response = client.chat.completions.create(
+  model="gpt-4o-mini",
+  messages=[
+    {
+      "role": "user",
+      "content": [
+        {"type": "text", "text": "What’s in this image?"},
+        {
+          "type": "image_url",
+          "image_url": {
+            "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
+          },
+        },
+      ],
+    }
+  ],
+  max_tokens=300,
+)
+
+print(response.choices[0])
+```
+
+## Manually logging images
+
+If you are not using the OpenAI SDK, you can still log images to the platform. The UI will automatically detect the image and display it if the input field has a `message` attribute that follows the OpenAI format:
+
+```json
+{
+    "messages": [
+        ...,
+        {
+            "type": "image_url",
+            "image_url": {
+                "url": "<url or base64 encoded image>"
+            }
+        }    
+    ],
+    ...
+}
+```
+
+:::tip
+Let's us know on [Github](https://github.com/comet-ml/opik/issues/new/choose) if you would like to us to support additional image formats or models.
+:::
diff --git a/apps/opik-documentation/documentation/sidebars.ts b/apps/opik-documentation/documentation/sidebars.ts
@@ -25,7 +25,7 @@ const sidebars: SidebarsConfig = {
       type: 'category',
       label: 'Tracing',
       collapsed: false,
-      items: ['tracing/log_traces', 'tracing/log_distributed_traces', 'tracing/annotate_traces', {
+      items: ['tracing/log_traces', 'tracing/log_multimodal_traces', 'tracing/log_distributed_traces', 'tracing/annotate_traces', {
         type: 'category',
         label: 'Integrations',
         collapsed: true,

diff --git a/apps/opik-documentation/documentation/static/img/tracing/image_trace.png b/apps/opik-documentation/documentation/static/img/tracing/image_trace.png