docs: update parallel integration (#2250)

jannikmaierhoefer · web-flow · commit 6f02acf9524e · 2025-10-31T15:04:29.000Z
diff --git a/cookbook/integration_parallel.ipynb b/cookbook/integration_parallel.ipynb
@@ -4,13 +4,13 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<!-- NOTEBOOK_METADATA source: \"⚠️ Jupyter Notebook\" title: \"Monitor Parallel AI Tasks with Langfuse\" sidebarTitle: \"Parallel AI\" logo: \"/images/integrations/parallel_icon.svg\" description: \"Learn how to trace Parallel AI task execution using Langfuse to capture detailed observability data for your AI workflow operations.\" category: \"Integrations\" -->\n",
+    "<!-- NOTEBOOK_METADATA source: \"⚠️ Jupyter Notebook\" title: \"Monitor Parallel Tasks with Langfuse\" sidebarTitle: \"Parallel\" logo: \"/images/integrations/parallel_icon.svg\" description: \"Learn how to trace Parallel task execution using Langfuse to capture detailed observability data for your AI workflow operations.\" category: \"Integrations\" -->\n",
     "\n",
-    "# Parallel AI Integration\n",
+    "# Parallel Integration\n",
     "\n",
-    "In this guide, we'll show you how to integrate [Langfuse](https://langfuse.com) with [Parallel AI](https://parallel.ai/) to trace your AI task operations. By leveraging Langfuse's tracing capabilities, you can automatically capture details such as inputs, outputs, and execution times of your Parallel AI tasks.\n",
+    "In this guide, we'll show you how to integrate [Langfuse](https://langfuse.com) with [Parallel](https://parallel.ai/) to trace your AI task operations. By leveraging Langfuse's tracing capabilities, you can automatically capture details such as inputs, outputs, and execution times of your Parallel tasks.\n",
     "\n",
-    "> **What is Parallel AI?** [Parallel AI](https://parallel.ai/) is an API service that enables you to execute AI tasks in parallel, optimizing workflow efficiency. It provides a powerful task API that allows you to run multiple AI operations concurrently, making it ideal for building scalable AI applications.\n",
+    "> **What is Parallel?** [Parallel](https://parallel.ai/) develops a suite of web search and web agent APIs that connect AI agents, applications, and workflows to the open internet, enabling programmable tasks from simple searches to complex knowledge work.\n",
     "\n",
     "> **What is Langfuse?** [Langfuse](https://langfuse.com) is an open source LLM engineering platform that helps teams trace API calls, monitor performance, and debug issues in their AI applications.\n",
     "\n",
@@ -33,7 +33,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Next, configure your environment with your Parallel AI and Langfuse API keys. You can get these keys by signing up for a free [Langfuse Cloud](https://cloud.langfuse.com/) account or by [self-hosting Langfuse](https://langfuse.com/self-hosting) and from the [Parallel AI dashboard](https://parallel.ai/)."
+    "Next, configure your environment with your Parallel and Langfuse API keys. You can get these keys by signing up for a free [Langfuse Cloud](https://cloud.langfuse.com/) account or by [self-hosting Langfuse](https://langfuse.com/self-hosting) and from the [Parallel dashboard](https://parallel.ai/)."
    ]
   },
   {
@@ -50,7 +50,7 @@
     "os.environ[\"LANGFUSE_HOST\"] = \"https://cloud.langfuse.com\" # 🇪🇺 EU region\n",
     "# os.environ[\"LANGFUSE_HOST\"] = \"https://us.cloud.langfuse.com\" # 🇺🇸 US region\n",
     "\n",
-    "# Your Parallel AI key\n",
+    "# Your Parallel key\n",
     "os.environ[\"PARALLEL_API_KEY\"] = \"...\"\n",
     "\n",
     "# Your openai key\n",
@@ -122,7 +122,7 @@
     "\n",
     "response = client.chat.completions.create(\n",
     "    model=\"speed\", # Parallel model name\n",
-    "    name=\"Parallel AI Chat\",\n",
+    "    name=\"Parallel Chat\",\n",
     "    messages=[\n",
     "        {\"role\": \"user\", \"content\": \"What does Parallel Web Systems do?\"}\n",
     "    ],\n",
@@ -161,7 +161,7 @@
    "source": [
     "## Example 3: Parallel Search API and OpenAI\n",
     "\n",
-    "You can also trace more complex workflows that involve summarizing the search results with OpenAI. Here we use the [Langfuse `@observe()` decorator](https://langfuse.com/docs/sdk/python/decorators) to group both the Parallel AI search and the OpenAI generation into one trace. "
+    "You can also trace more complex workflows that involve summarizing the search results with OpenAI. Here we use the [Langfuse `@observe()` decorator](https://langfuse.com/docs/sdk/python/decorators) to group both the Parallel search and the OpenAI generation into one trace. "
    ]
   },
   {
@@ -183,7 +183,7 @@
     "\n",
     "    @observe(as_type=\"retriever\")\n",
     "    def search_with_parallel(objective, search_queries, num_results: int = 5):\n",
-    "        \"\"\"Search the web using Parallel AI and return results.\"\"\"\n",
+    "        \"\"\"Search the web using Parallel and return results.\"\"\"\n",
     "        search = parallel_client.beta.search(\n",
     "            objective=objective,\n",
     "            search_queries=search_queries,\n",
@@ -231,7 +231,7 @@
     "- Input prompts and output results\n",
     "- Performance metrics for each task\n",
     "\n",
-    "![Parallel AI Example trace in Langfuse UI](https://langfuse.com/images/cookbook/integration_parallel-ai/parallel-ai-example-trace.png)\n",
+    "![Parallel Example trace in Langfuse UI](https://langfuse.com/images/cookbook/integration_parallel-ai/parallel-ai-example-trace.png)\n",
     "\n",
     "[Example trace in Langfuse](https://cloud.langfuse.com/project/cloramnkj0002jz088vzn1ja4/traces/a664e35ab40a75d04cf6a262d0399f05?timestamp=2025-10-28T15%3A16%3A26.617Z&observation=13fc56583aafeb06)\n",
     "\n",
diff --git a/pages/integrations/other/parallel-ai.mdx b/pages/integrations/other/parallel-ai.mdx
@@ -1,17 +1,17 @@
 ---
 source: ⚠️ Jupyter Notebook
-title: Monitor Parallel AI Tasks with Langfuse
-sidebarTitle: Parallel AI
+title: Monitor Parallel Tasks with Langfuse
+sidebarTitle: Parallel
 logo: /images/integrations/parallel_icon.svg
-description: Learn how to trace Parallel AI task execution using Langfuse to capture detailed observability data for your AI workflow operations.
+description: Learn how to trace Parallel task execution using Langfuse to capture detailed observability data for your AI workflow operations.
 category: Integrations
 ---
 
-# Parallel AI Integration
+# Parallel Integration
 
-In this guide, we'll show you how to integrate [Langfuse](https://langfuse.com) with [Parallel AI](https://parallel.ai/) to trace your AI task operations. By leveraging Langfuse's tracing capabilities, you can automatically capture details such as inputs, outputs, and execution times of your Parallel AI tasks.
+In this guide, we'll show you how to integrate [Langfuse](https://langfuse.com) with [Parallel](https://parallel.ai/) to trace your AI task operations. By leveraging Langfuse's tracing capabilities, you can automatically capture details such as inputs, outputs, and execution times of your Parallel tasks.
 
-> **What is Parallel AI?** [Parallel AI](https://parallel.ai/) is an API service that enables you to execute AI tasks in parallel, optimizing workflow efficiency. It provides a powerful task API that allows you to run multiple AI operations concurrently, making it ideal for building scalable AI applications.
+> **What is Parallel?** [Parallel](https://parallel.ai/) develops a suite of web search and web agent APIs that connect AI agents, applications, and workflows to the open internet, enabling programmable tasks from simple searches to complex knowledge work.
 
 > **What is Langfuse?** [Langfuse](https://langfuse.com) is an open source LLM engineering platform that helps teams trace API calls, monitor performance, and debug issues in their AI applications.
 
@@ -25,7 +25,7 @@ First, install the necessary Python packages:
 %pip install langfuse parallel-web openai
 ```
 
-Next, configure your environment with your Parallel AI and Langfuse API keys. You can get these keys by signing up for a free [Langfuse Cloud](https://cloud.langfuse.com/) account or by [self-hosting Langfuse](https://langfuse.com/self-hosting) and from the [Parallel AI dashboard](https://parallel.ai/).
+Next, configure your environment with your Parallel and Langfuse API keys. You can get these keys by signing up for a free [Langfuse Cloud](https://cloud.langfuse.com/) account or by [self-hosting Langfuse](https://langfuse.com/self-hosting) and from the [Parallel dashboard](https://parallel.ai/).
 
 
 ```python
@@ -37,7 +37,7 @@ os.environ["LANGFUSE_SECRET_KEY"] = "sk-lf-..."
 os.environ["LANGFUSE_HOST"] = "https://cloud.langfuse.com" # 🇪🇺 EU region
 # os.environ["LANGFUSE_HOST"] = "https://us.cloud.langfuse.com" # 🇺🇸 US region
 
-# Your Parallel AI key
+# Your Parallel key
 os.environ["PARALLEL_API_KEY"] = "..."
 
 # Your openai key
@@ -91,7 +91,7 @@ client = OpenAI(
 
 response = client.chat.completions.create(
     model="speed", # Parallel model name
-    name="Parallel AI Chat",
+    name="Parallel Chat",
     messages=[
         {"role": "user", "content": "What does Parallel Web Systems do?"}
     ],
@@ -126,7 +126,7 @@ print(response.choices[0].message.content)
 
 ## Example 3: Parallel Search API and OpenAI
 
-You can also trace more complex workflows that involve summarizing the search results with OpenAI. Here we use the [Langfuse `@observe()` decorator](https://langfuse.com/docs/sdk/python/decorators) to group both the Parallel AI search and the OpenAI generation into one trace. 
+You can also trace more complex workflows that involve summarizing the search results with OpenAI. Here we use the [Langfuse `@observe()` decorator](https://langfuse.com/docs/sdk/python/decorators) to group both the Parallel search and the OpenAI generation into one trace. 
 
 
 ```python
@@ -143,7 +143,7 @@ def search_and_summarize(objective, search_queries):
 
     @observe(as_type="retriever")
     def search_with_parallel(objective, search_queries, num_results: int = 5):
-        """Search the web using Parallel AI and return results."""
+        """Search the web using Parallel and return results."""
         search = parallel_client.beta.search(
             objective=objective,
             search_queries=search_queries,
@@ -187,7 +187,7 @@ After executing the traced functions, log in to your [Langfuse Dashboard](https:
 - Input prompts and output results
 - Performance metrics for each task
 
-![Parallel AI Example trace in Langfuse UI](https://langfuse.com/images/cookbook/integration_parallel-ai/parallel-ai-example-trace.png)
+![Parallel Example trace in Langfuse UI](https://langfuse.com/images/cookbook/integration_parallel-ai/parallel-ai-example-trace.png)
 
 [Example trace in Langfuse](https://cloud.langfuse.com/project/cloramnkj0002jz088vzn1ja4/traces/a664e35ab40a75d04cf6a262d0399f05?timestamp=2025-10-28T15%3A16%3A26.617Z&observation=13fc56583aafeb06)
 </Steps>
