Merge branch 'azure-partner' of https://github.com/Portkey-AI/docs-core into azure-partner

Author: vrushankportkey

changelog/enterprise.mdx

@@ -1,12 +1,45 @@
 ---
 title: "Enterprise Gateway"
-sidebarTitle: "Enterprise Gateway [1.10.21]"
+sidebarTitle: "Enterprise Gateway [1.10.22]"
 ---
 
 <Card title="Schedule Call" href="https://portkey.sh/demo-21" icon="calendar" horizontal>
 Discuss how Portkey's AI Gateway can enhance your organization's AI infrastructure
 </Card>
 
+<Update label="1.10.22" description="2025-05-08">
+## v1.10.22
+---
+### Enhanced Anthropic PDF Support
+- Added transformation logic to support OpenAI-spec-compatible `file` content parts in request.
+- Introduced two new Portkey parameters for the `file` content parts: `file_url` and `mime_type`.
+- Applicable for Anthropic, Bedrock-Anthropic and VertexAI-Anthropic models.
+- [Docs](/integrations/llms/anthropic#processing-pdfs-with-claude)
+
+### OTEL Configurations
+- Added two new environment variables:
+    - `OTEL_SERVICE_NAME`: Sets the `service.name` resource attribute value.
+    - `OTEL_RESOURCE_ATTRIBUTES`: Comma-separated `key=value` pairs which will be sent as individual resource attributes.
+
+### New Providers
+- **Ncompass**: Supports chat completions endpoint.
+- **Lepton**: Supports chat completions, completions and transcriptions endpoints.
+- **Snowflake Cortex**: Supports chat completions endpoint.
+
+### Provider Updates
+- **Groq**: Handled an exception that occurred when `stream_options` was included in the request, because the response transformer was not handling `usage` chunk mapping as expected.
+- **Workers AI**: Added support for `/images/generations` route.
+- **Openrouter**: Added support for `usage` request parameter and response mapping.
+- **Deepinfra**: Handled `ping` event returned in stream and mapped `usage` field returned in the response.
+- **VertexAI**: Now returns 400 (instead of 500) for empty model validation errors.
+
+### Fixes And Improvements
+- For providers except OpenAI and Azure-OpenAI, updated the value of `object` field in chat completions response from `chat_completion` to `chat.completion` for OpenAI spec compliance.
+- **Proxy (Passthrough) Requests**: Fixed endpoint construction logic, which was affecting a few provider-route combinations.
+- **Unified Batches**: Fixed issue where embeddings batch output was being returned as empty.
+- **Prometheus**: Fixed issue where `model` label was set as N/A for Bedrock requests.
+</Update>
+
 <Update label="1.10.21" description="2025-04-30">
 ## v1.10.21
 ---

docs.json

@@ -2214,6 +2214,10 @@
     {
       "source": "/guides/use-cases/build-a-chatbot-using-portkeys-prompt-templates",
       "destination": "/guides/prompts/build-a-chatbot-using-portkeys-prompt-templates"
+    },
+    {
+      "source": "/integrations/tools/exa",
+      "destination": "/integrations/plugins/exa"
     }
   ],
   "seo": {

images/product/logs-export-1.png

@@ -490,11 +490,20 @@ Currently, Portkey supports PDF processing using base64-encoded PDF documents, f
                         "text": "What are the key findings in this document?"
                     },
                     {
-                        "type": "image_url",
-                        "image_url": {
-                            "url": pdf_data
-                        }
+                      "type": "file",
+                      "file": {
+                          # "file_url": "https://pdfobject.com/pdf/sample.pdf", # if you want to pass a pdf file from a url
+                          "mime_type": "application/pdf",
+                          "file_data": "BASE64_PDF_DATA"
+                      }
                     }
+                    # { # if you want to pass a plain text file
+                    #     "type": "file",
+                    #     "file": {
+                    #         "mime_type": "text/plain",
+                    #         "file_data": "This is a plain text file"
+                    #     }
+                    # }
                 ]
             }
         ]
@@ -544,11 +553,20 @@ Currently, Portkey supports PDF processing using base64-encoded PDF documents, f
                 text: "What are the key findings in this document?"
               },
               {
-                type: "image_url",
-                image_url: {
-                  url: pdfData
+                type: "file",
+                file: {
+                  mime_type: "application/pdf",
+                  file_data: pdfData,
+                  // file_url: "https://pdfobject.com/pdf/sample.pdf" // if you want to pass a pdf file from a url
                 }
-              }
+              },
+              // { // if you want to pass a plain text file
+              //     "type": "file",
+              //     "file": {
+              //         "mime_type": "text/plain",
+              //         "file_data": "This is a plain text file"
+              //     }
+              // }
             ]
           }
         ]
@@ -591,11 +609,19 @@ Currently, Portkey supports PDF processing using base64-encoded PDF documents, f
                 "text": "What are the key findings in this document?"
               },
               {
-                "type": "image_url",
-                "image_url": {
-                  "url": "data:application/pdf;base64,'$PDF_BASE64'"
+                "type": "file",
+                "file": {
+                  "mime_type": "application/pdf",
+                  "file_data": "BASE64_PDF_DATA"
                 }
               }
+              // { // if you want to pass a plain text file
+              //     "type": "file",
+              //     "file": {
+              //         "mime_type": "text/plain",
+              //         "file_data": "This is a plain text file"
+              //     }
+              // }
             ]
           }
         ]
@@ -604,10 +630,6 @@ Currently, Portkey supports PDF processing using base64-encoded PDF documents, f
   </Tab>
 </Tabs>
 
-<Note>
-  We are currently working on enabling direct URL-based PDF support for Anthropic. Stay tuned for updates!
-</Note>
-
 
 ### Best Practices for PDF Processing
 

images/product/logs-export-2.png

@@ -70,6 +70,11 @@ This process allows any LLM to respond with up-to-date knowledge without retrain
 
 * Save this config and note its Config ID for use in your requests
 
+
+<Note>
+    The Exa Plugin is supported only as an `input guardrail`. It adds web search results to your request before it reaches the LLM, which is why only `before_request_hooks` are supported and not `after_request_hooks` on Portkey's gateway. [Learn more about guardrails here](/product/guardrails)
+</Note>
+
 ### 4. Use the Config in Your Requests
 
 <Tabs>

integrations/llms/anthropic.mdx

@@ -0,0 +1,72 @@
+---
+title: "(DEPRECATED) Logs Export"
+description: "Easily access your Portkey logs data for further analysis and reporting"
+---
+
+<Info>
+   Logs export feature is only available for [**Production**](https://portkey.ai/pricing) and [**Enterprise**](https://portkey.ai/docs/product/enterprise-offering) users.
+</Info>
+
+<Note>
+Portkey offers an in-app logs export feature that is not generally available yet. If you're interested in early access, contact us at [email protected].
+</Note>
+
+At Portkey, we understand the importance of data analysis and reporting for businesses and teams. That's why we provide a comprehensive logs export feature for our paid users. With this feature, you can easily request and obtain your Portkey logs data in a **structured JSON** format, allowing you to gain valuable insights into your LLM usage, performance, costs, and more.
+
+## Requesting Logs Export
+
+To submit a data export request, simply follow these steps:
+
+1. Ensure you are an admin of your organization on Portkey.
+2. Send an email to [[email protected]](mailto:[email protected]) with the subject line `Logs Export - [Your_Organization_Name]`.
+3. In the email body,
+   * Specify the **time frame** for which you require the logs data. **Pro plan** supports logs export of **last 30** days.
+   * Share names of the **specific columns** you require (see the "[Exported Data](/product/observability/logs-export#exported-data)" section below for a complete list of available columns).
+4. Our team will process your request and provide you with the exported logs data in JSON format.
+
+<Note>
+   Note: Portkey only supports data exports in the `JSONL` format, and can not process exports in any other formats at the moment.
+</Note>
+
+## Exported Data
+
+The exported logs data will include the following columns:
+
+| Column Name            | Column Description / Property                             |
+| ---------------------- | --------------------------------------------------------- |
+| created\_at            | Timestamp of the request                                  |
+| request.body           | Request JSON payload (as seen in the Portkey logs)        |
+| response.body          | Response JSON payload (as seen in the Portkey logs)       |
+| is\_success            | Request success status (1 = success, 0 = failure)         |
+| ai\_org                | AI provider name                                          |
+| ai\_model              | AI model name                                             |
+| req\_units             | Number of tokens in the request                           |
+| res\_units             | Number of tokens in the response                          |
+| total\_units           | Total number of tokens (request + response)               |
+| cost                   | Cost of the request in cents (USD)                        |
+| cost\_currency         | Currency of the cost (USD)                                |
+| request\_url           | Final provider API URL                                    |
+| request\_method        | HTTP request method                                       |
+| response\_status\_code | HTTP response status code                                 |
+| response\_time         | Response time in milliseconds                             |
+| cache\_status          | Cache status (SEMANTIC HIT, HIT, MISS, DISABLED)          |
+| cache\_type            | Cache type (SIMPLE, SEMANTIC)                             |
+| stream\_mode           | Stream mode status (TRUE, FALSE)                          |
+| retry\_success\_count  | Number of retries after which request was successful      |
+| trace\_id              | Trace ID for the request                                  |
+| mode                   | Config top level strategy (SINGLE, FALLBACK, LOADBALANCE) |
+| virtual\_key           | Virtual key used for the request                          |
+| runtime                | Runtime environment                                       |
+| runtime\_version       | Runtime environment version                               |
+| sdk\_version           | Portkey SDK version                                       |
+| config                 | Config ID used for the request                            |
+| prompt\_slug           | Prompt ID used for the request                            |
+| prompt\_version\_id    | Version number of the prompt template slug                |
+| metadata.key           | Custom metadata key                                       |
+| metadata.value         | Custom metadata value                                     |
+
+With this comprehensive data, you can analyze your API usage patterns, monitor performance, optimize costs, and make data-driven decisions for your business or team.
+
+## Support
+
+If you have any questions or need assistance with the logs export feature, reach out to the Portkey team at [email protected] or hop on to our [Discord server](https://portkey.ai/community).