diff --git a/fern/definition/gdpr-privacy.yml b/fern/definition/gdpr-privacy.yml index 38e77ff..909ed4d 100644 --- a/fern/definition/gdpr-privacy.yml +++ b/fern/definition/gdpr-privacy.yml @@ -22,7 +22,7 @@ service: docs: | By default, all prompts and responses are logged. - If you’ve disabled this behavior by following [this guide](/open-ll-metry/privacy/prompts-completions-and-embeddings), and then selectively enabled it for some of your users, then you can use this API to view which users you’ve enabled. + If you’ve disabled this behavior by following [this guide](/docs/openllmetry/privacy/prompts-completions-and-embeddings), and then selectively enabled it for some of your users, then you can use this API to view which users you’ve enabled. path: "/data-deletion" request: name: GetDeletionStatusRequest diff --git a/fern/definition/tracing.yml b/fern/definition/tracing.yml index 3076ec1..93b0333 100644 --- a/fern/definition/tracing.yml +++ b/fern/definition/tracing.yml @@ -9,7 +9,7 @@ service: docs: | By default, all prompts and responses are logged. - If you want to disable this behavior by following [this guide](/open-ll-metry/privacy/prompts-completions-and-embeddings), you can selectively enable it for some of your users with this API. + If you want to disable this behavior by following [this guide](/docs/openllmetry/privacy/prompts-completions-and-embeddings), you can selectively enable it for some of your users with this API. path: "/tracing-allow-list" method: POST request: EnableLogging @@ -20,7 +20,7 @@ service: docs: | By default, all prompts and responses are logged. - If you’ve disabled this behavior by following [this guide](/open-ll-metry/privacy/prompts-completions-and-embeddings), and then selectively enabled it for some of your users, then you can use this API to view which users you’ve enabled. + If you’ve disabled this behavior by following [this guide](/docs/openllmetry/privacy/prompts-completions-and-embeddings), and then selectively enabled it for some of your users, then you can use this API to view which users you’ve enabled. path: "/tracing-allow-list" method: GET response: GetIdentifiersResponse @@ -32,7 +32,7 @@ service: docs: | By default, all prompts and responses are logged. - If you’ve disabled this behavior by following [this guide](/open-ll-metry/privacy/prompts-completions-and-embeddings), and then selectively enabled it for some of your users, then you can use this API to disable it for previously enabled ones. + If you’ve disabled this behavior by following [this guide](/docs/openllmetry/privacy/prompts-completions-and-embeddings), and then selectively enabled it for some of your users, then you can use this API to disable it for previously enabled ones. path: "/tracing-allow-list" method: DELETE request: DisableLogging diff --git a/fern/docs.yml b/fern/docs.yml index 917358a..5bd2069 100644 --- a/fern/docs.yml +++ b/fern/docs.yml @@ -1,6 +1,6 @@ instances: - url: traceloop.docs.buildwithfern.com/docs - custom-domain: traceloop.com/docs + custom-domain: fern.traceloop.com/docs title: Traceloop | Docs @@ -15,7 +15,7 @@ tabs: api: display-name: Dashboard API icon: "fa-duotone fa-webhook" - + slug: dashboard-api navigation: - tab: docs layout: diff --git a/fern/pages/documentation/learn/intro.mdx b/fern/pages/documentation/learn/intro.mdx index c2d9930..f789db9 100644 --- a/fern/pages/documentation/learn/intro.mdx +++ b/fern/pages/documentation/learn/intro.mdx @@ -19,28 +19,28 @@ Traceloop natively plugs into OpenLLMetry SDK. To get started, pick the language Available Available Beta Beta diff --git a/fern/pages/documentation/prompt-management/fetching-prompts.mdx b/fern/pages/documentation/prompt-management/fetching-prompts.mdx index d1fc6c5..cfa3b19 100644 --- a/fern/pages/documentation/prompt-management/fetching-prompts.mdx +++ b/fern/pages/documentation/prompt-management/fetching-prompts.mdx @@ -10,7 +10,7 @@ The default poll interval is 60 seconds but can be configured with the `TRACELOO To disable polling all together, set the `TRACELOOP_SYNC_ENABLED` environment variable to false (its enabled by default). -Make sure you’ve configured the SDK with the right environment and API Key. See the [SDK documentation](/open-ll-metry/integrations/traceloop) for more information. +Make sure you’ve configured the SDK with the right environment and API Key. See the [SDK documentation](/docs/openllmetry/integrations/traceloop) for more information. The SDK uses smart caching mechanisms to proide zero latency for fetching prompts. diff --git a/fern/pages/documentation/prompt-management/prompt-registry.mdx b/fern/pages/documentation/prompt-management/prompt-registry.mdx index 6e89c39..e8894e2 100644 --- a/fern/pages/documentation/prompt-management/prompt-registry.mdx +++ b/fern/pages/documentation/prompt-management/prompt-registry.mdx @@ -53,7 +53,7 @@ Here, you can see all recent prompt versions, and which environments they are de As a safeguard, you cannot deploy a prompt to the `Staging` environment before first deploying it to `Development`. Similarly, you cannot deploy to `Production` without first deploying to `Staging`. -To fetch prompts from a specific environment, you must supply that environment’s API key to the Traceloop SDK. See the [SDK Configuration](/open-ll-metry/integrations/traceloop) for details +To fetch prompts from a specific environment, you must supply that environment’s API key to the Traceloop SDK. See the [SDK Configuration](/docs/openllmetry/integrations/traceloop) for details ## Prompt Versions diff --git a/fern/pages/documentation/prompt-management/quickstart.mdx b/fern/pages/documentation/prompt-management/quickstart.mdx index 1b82ece..178bf65 100644 --- a/fern/pages/documentation/prompt-management/quickstart.mdx +++ b/fern/pages/documentation/prompt-management/quickstart.mdx @@ -1,11 +1,11 @@ -
+ ![prompt-management-quickstart](https://fern-image-hosting.s3.amazonaws.com/traceloop/prompt-management-quickstart.png) -
+ You can use Traceloop to manage your prompts and model configurations. That way you can easily experiment with different prompts, and rollout changes gradually and safely. -Make sure you’ve created an API key and set it as an environment variable `TRACELOOP_API_KEY` before you start. Check out the SDK’s [getting started guide](/open-ll-metry/quick-start/python) for more information. +Make sure you’ve created an API key and set it as an environment variable `TRACELOOP_API_KEY` before you start. Check out the SDK’s [getting started guide](/docs/openllmetry/quick-start/python) for more information. diff --git a/fern/pages/openllmetry/integrations/opentelemetry-collector.mdx b/fern/pages/openllmetry/integrations/opentelemetry-collector.mdx index a27cbfc..065810a 100644 --- a/fern/pages/openllmetry/integrations/opentelemetry-collector.mdx +++ b/fern/pages/openllmetry/integrations/opentelemetry-collector.mdx @@ -8,4 +8,4 @@ Since Traceloop is emitting standard OTLP HTTP (standard OpenTelemetry protocol) TRACELOOP_BASE_URL=https://:4318 ``` -You can connect your collector to Traceloop by following the instructions in the [Traceloop integration section](/open-ll-metry/integrations/traceloop#using-an-opentelemetry-collector). \ No newline at end of file +You can connect your collector to Traceloop by following the instructions in the [Traceloop integration section](/docs/openllmetry/integrations/traceloop#using-an-opentelemetry-collector). \ No newline at end of file diff --git a/fern/pages/openllmetry/integrations/overview.mdx b/fern/pages/openllmetry/integrations/overview.mdx index ae3cd18..0ace824 100644 --- a/fern/pages/openllmetry/integrations/overview.mdx +++ b/fern/pages/openllmetry/integrations/overview.mdx @@ -7,19 +7,19 @@ Since Traceloop SDK is using OpenTelemetry under the hood, you can see everythin ## The Integrations Catalog - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + \ No newline at end of file diff --git a/fern/pages/openllmetry/integrations/traceloop.mdx b/fern/pages/openllmetry/integrations/traceloop.mdx index 6316622..3979423 100644 --- a/fern/pages/openllmetry/integrations/traceloop.mdx +++ b/fern/pages/openllmetry/integrations/traceloop.mdx @@ -55,6 +55,6 @@ excerpt: LLM Observability with Traceloop exporters: [otlp/traceloop] ``` - You can route OpenLLMetry to your collector by following the [OpenTelemetry Collector](/open-ll-metry/integrations/open-telemetry-collector) integration instructions. + You can route OpenLLMetry to your collector by following the [OpenTelemetry Collector](/docs/openllmetry/integrations/open-telemetry-collector) integration instructions. \ No newline at end of file diff --git a/fern/pages/openllmetry/intro/what-is-llmetry.mdx b/fern/pages/openllmetry/intro/what-is-llmetry.mdx index d403dcf..41efd18 100644 --- a/fern/pages/openllmetry/intro/what-is-llmetry.mdx +++ b/fern/pages/openllmetry/intro/what-is-llmetry.mdx @@ -53,22 +53,22 @@ You can use OpenLLMetry whether you use a framework like LangChain, or directly ## Getting Started - + Set up Traceloop Python SDK in your project - + Set up Traceloop Javascript SDK in your project - + Set up Traceloop Go SDK in your project - + Learn how to annotate your code to enrich your traces - + Learn how to connect to your existing observability stack - + How we secure your data diff --git a/fern/pages/openllmetry/privacy/prompts-completions-embeddings.mdx b/fern/pages/openllmetry/privacy/prompts-completions-embeddings.mdx index 9b2f9b1..a35bc40 100644 --- a/fern/pages/openllmetry/privacy/prompts-completions-embeddings.mdx +++ b/fern/pages/openllmetry/privacy/prompts-completions-embeddings.mdx @@ -56,7 +56,7 @@ You can decide to selectively enable or disable prompt logging for specific user - We have an API to enable content tracing for specific users, as defined by [association entities](/open-ll-metry/tracing/associating-entities-with-traces). See the [Traceloop API documentation](/dashboard-api/endpoints) for more information. + We have an API to enable content tracing for specific users, as defined by [association entities](/docs/openllmetry/tracing/associating-entities-with-traces). See the [Traceloop API documentation](/docs/dashboard-api/endpoints) for more information. Set a key called `override_enable_content_tracing` in the OpenTelemetry context to `True` right before making the LLM call you want to trace with prompts. This will create a new context that will instruct instrumentations to log prompts and completions as span attributes. diff --git a/fern/pages/openllmetry/quickstart/go.mdx b/fern/pages/openllmetry/quickstart/go.mdx index 25a77c6..66a13f0 100644 --- a/fern/pages/openllmetry/quickstart/go.mdx +++ b/fern/pages/openllmetry/quickstart/go.mdx @@ -99,7 +99,7 @@ func call_llm() { Lastly, you’ll need to configure where to export your traces. The 2 environment variables controlling this are `TRACELOOP_API_KEY` and `TRACELOOP_BASE_URL`. -For Traceloop, read on. For other options, see [Exporting](/open-ll-metry/integrations/overview). +For Traceloop, read on. For other options, see [Exporting](/docs/openllmetry/integrations/overview). ### Using Traceloop Cloud diff --git a/fern/pages/openllmetry/quickstart/next.mdx b/fern/pages/openllmetry/quickstart/next.mdx index 7f298d5..55c8de2 100644 --- a/fern/pages/openllmetry/quickstart/next.mdx +++ b/fern/pages/openllmetry/quickstart/next.mdx @@ -158,7 +158,7 @@ You can check out our full working example with Next.js 13 [here](https://github f you have complex workflows or chains, you can annotate them to get a better understanding of what’s going on. You’ll see the complete trace of your workflow on Traceloop or any other dashboard you’re using. - We have a set of [methods and decorators](/open-ll-metry/tracing/workflows-tasks-agents-and-tools) to make this easier. Assume you have a function that renders a prompt and calls an LLM, simply wrap it in a `withWorkflow()` function call. + We have a set of [methods and decorators](/docs/openllmetry/tracing/workflows-tasks-agents-and-tools) to make this easier. Assume you have a function that renders a prompt and calls an LLM, simply wrap it in a `withWorkflow()` function call. We also have compatible Typescript decorators for class methods which are more convenient. @@ -188,13 +188,13 @@ You can check out our full working example with Next.js 13 [here](https://github - For more information, see the [dedicated section in the docs](/open-ll-metry/tracing/workflows-tasks-agents-and-tools). + For more information, see the [dedicated section in the docs](/docs/openllmetry/tracing/workflows-tasks-agents-and-tools). ### Configure Trace Exporting Lastly, you’ll need to configure where to export your traces. The 2 environment variables controlling this are `TRACELOOP_API_KEY` and `TRACELOOP_BASE_URL`. - For Traceloop, read on. For other options, see [Exporting](/open-ll-metry/integrations/overview). + For Traceloop, read on. For other options, see [Exporting](/docs/openllmetry/integrations/overview). ### Using Traceloop Cloud diff --git a/fern/pages/openllmetry/quickstart/node.mdx b/fern/pages/openllmetry/quickstart/node.mdx index 2ad6a56..0d3cb16 100644 --- a/fern/pages/openllmetry/quickstart/node.mdx +++ b/fern/pages/openllmetry/quickstart/node.mdx @@ -54,7 +54,7 @@ traceloop.initialize({ disableBatch: true }); If you have complex workflows or chains, you can annotate them to get a better understanding of what’s going on. You’ll see the complete trace of your workflow on Traceloop or any other dashboard you’re using. -We have a set of [methods and decorators](/open-ll-metry/tracing/workflows-tasks-agents-and-tools) to make this easier. Assume you have a function that renders a prompt and calls an LLM, simply wrap it in a `withWorkflow()` function call. +We have a set of [methods and decorators](/docs/openllmetry/tracing/workflows-tasks-agents-and-tools) to make this easier. Assume you have a function that renders a prompt and calls an LLM, simply wrap it in a `withWorkflow()` function call. We also have compatible Typescript decorators for class methods which are more convenient. @@ -84,13 +84,13 @@ If you’re using an LLM framework like Haystack, Langchain or LlamaIndex - we -For more information, see the [dedicated section in the docs](/open-ll-metry/tracing/workflows-tasks-agents-and-tools). +For more information, see the [dedicated section in the docs](/docs/openllmetry/tracing/workflows-tasks-agents-and-tools). ### Configure Trace Exporting Lastly, you’ll need to configure where to export your traces. The 2 environment variables controlling this are `TRACELOOP_API_KEY` and `TRACELOOP_BASE_URL`. -For Traceloop, read on. For other options, see [Exporting](/open-ll-metry/integrations/overview). +For Traceloop, read on. For other options, see [Exporting](/docs/openllmetry/integrations/overview). ### Using Traceloop Cloud diff --git a/fern/pages/openllmetry/quickstart/python.mdx b/fern/pages/openllmetry/quickstart/python.mdx index be9449b..c768b06 100644 --- a/fern/pages/openllmetry/quickstart/python.mdx +++ b/fern/pages/openllmetry/quickstart/python.mdx @@ -45,7 +45,7 @@ Traceloop.init(disable_batch=True) If you have complex workflows or chains, you can annotate them to get a better understanding of what’s going on. You’ll see the complete trace of your workflow on Traceloop or any other dashboard you’re using. -We have a set of [decorators](/open-ll-metry/tracing/workflows-tasks-agents-and-tools) to make this easier. Assume you have a function that renders a prompt and calls an LLM, simply add `@workflow` (or for asynchronous methods - `@aworkflow`). +We have a set of [decorators](/docs/openllmetry/tracing/workflows-tasks-agents-and-tools) to make this easier. Assume you have a function that renders a prompt and calls an LLM, simply add `@workflow` (or for asynchronous methods - `@aworkflow`). If you’re using an LLM framework like Haystack, Langchain or LlamaIndex - we’ll do that for you. No need to add any annotations to your code. @@ -60,13 +60,13 @@ def suggest_answers(question: str): ... ``` -For more information, see the [dedicated section in the docs](/open-ll-metry/tracing/workflows-tasks-agents-and-tools). +For more information, see the [dedicated section in the docs](/docs/openllmetry/tracing/workflows-tasks-agents-and-tools). ### Configure trace exporting Lastly, you’ll need to configure where to export your traces. The 2 environment variables controlling this are `TRACELOOP_API_KEY` and `TRACELOOP_BASE_URL`. -For Traceloop, read on. For other options, see [Exporting](/open-ll-metry/integrations/overview). +For Traceloop, read on. For other options, see [Exporting](/docs/openllmetry/integrations/overview). ### Using Traceloop Cloud diff --git a/fern/pages/openllmetry/quickstart/ruby.mdx b/fern/pages/openllmetry/quickstart/ruby.mdx index 37d43e8..72a05b3 100644 --- a/fern/pages/openllmetry/quickstart/ruby.mdx +++ b/fern/pages/openllmetry/quickstart/ruby.mdx @@ -72,7 +72,7 @@ end Lastly, you’ll need to configure where to export your traces. The 2 environment variables controlling this are `TRACELOOP_API_KEY` and `TRACELOOP_BASE_URL`. -For Traceloop, read on. For other options, see [Exporting](/open-ll-metry/integrations/overview). +For Traceloop, read on. For other options, see [Exporting](/docs/openllmetry/integrations/overview). ### Using Traceloop Cloud diff --git a/fern/pages/openllmetry/quickstart/sdk-initialization.mdx b/fern/pages/openllmetry/quickstart/sdk-initialization.mdx index 20ac647..694cb3d 100644 --- a/fern/pages/openllmetry/quickstart/sdk-initialization.mdx +++ b/fern/pages/openllmetry/quickstart/sdk-initialization.mdx @@ -41,7 +41,7 @@ This defines the OpenTelemetry endpoint to connect to. It defaults to https://ap If you prefix it with `http` or `https`, it will use the OTLP/HTTP protocol. Otherwise, it will use the OTLP/GRPC protocol. -For configuring this to different observability platform, check out our [integrations section](/open-ll-metry/integrations/overview). +For configuring this to different observability platform, check out our [integrations section](/docs/openllmetry/integrations/overview). The OpenTelemetry standard defines that the actual endpoint should always end with `/v1/traces`. Thus, if you specify a base URL, we always append `/v1/traces` to it. This is similar to how `OTLP_EXPORTER_OTLP_ENDPOINT` works in all OpenTelemetry SDKs. @@ -69,7 +69,7 @@ The OpenTelemetry standard defines that the actual endpoint should always end wi If set, this is sent as a bearer token on the Authorization header. -[Traceloop](/open-ll-metry/integrations/traceloop), for example, use this to authenticate incoming traces and requests. +[Traceloop](/docs/openllmetry/integrations/traceloop), for example, use this to authenticate incoming traces and requests. If this is not set, and the base URL is set to `https://api.traceloop.com`, the SDK will generate a new API key automatically with the Traceloop dashboard. diff --git a/fern/pages/openllmetry/quickstart/troubleshooting.mdx b/fern/pages/openllmetry/quickstart/troubleshooting.mdx index 5356d98..f2f9211 100644 --- a/fern/pages/openllmetry/quickstart/troubleshooting.mdx +++ b/fern/pages/openllmetry/quickstart/troubleshooting.mdx @@ -11,7 +11,7 @@ We’ve all been there. You followed all the instructions, but you’re not seei ### Disable batch sending -Sending traces in batch is useful in production, but can be confusing if you’re working locally. Make sure you’ve [disabled batch sending](/open-ll-metry/quick-start/sdk-initialization-options#disable-batch). +Sending traces in batch is useful in production, but can be confusing if you’re working locally. Make sure you’ve [disabled batch sending](/docs/openllmetry/quick-start/sdk-initialization-options#disable-batch). @@ -44,7 +44,7 @@ import OpenAI from "openai"; // ... ``` -If that doesn’t work, you may need to manually instrument the libraries you’re using. See the [manual instrumentation guide](/open-ll-metry/tracing/manual-implementations-typescript-javascript) for more details. +If that doesn’t work, you may need to manually instrument the libraries you’re using. See the [manual instrumentation guide](/docs/openllmetry/tracing/manual-implementations-typescript-javascript) for more details. ```javascript import OpenAI from "openai"; @@ -85,7 +85,7 @@ Use the `ConsoleExporter` and check if you see traces in the console. -If you see traces in the console, then you probable haven’t configured the exporter properly. Check the [integration guide](/open-ll-metry/integrations/overview) again, and make sure you’re using the right endpoint and API key. +If you see traces in the console, then you probable haven’t configured the exporter properly. Check the [integration guide](/docs/openllmetry/integrations/overview) again, and make sure you’re using the right endpoint and API key. ### Talk to us! diff --git a/fern/pages/openllmetry/tracing/tracking-feedback.mdx b/fern/pages/openllmetry/tracing/tracking-feedback.mdx index f77dcb5..95e7411 100644 --- a/fern/pages/openllmetry/tracing/tracking-feedback.mdx +++ b/fern/pages/openllmetry/tracing/tracking-feedback.mdx @@ -1,6 +1,6 @@ When building LLM applications, it quickly becomes highly useful and important to track user feedback on the result of your LLM workflow. -Doing that with OpenLLMetry is easy. First, make sure you [associate your LLM workflow with unique identifiers](/open-ll-metry/tracing/associating-entities-with-traces). +Doing that with OpenLLMetry is easy. First, make sure you [associate your LLM workflow with unique identifiers](/docs/openllmetry/tracing/associating-entities-with-traces). Then, you can simply log a user feedback by calling our Python SDK or Typescript SDK. Feedbacks are always between -1 and 1, where -1 is the worst possible feedback and 1 is the best possible feedback. diff --git a/fern/pages/openllmetry/tracing/workflows-tasks-agents-tools.mdx b/fern/pages/openllmetry/tracing/workflows-tasks-agents-tools.mdx index 4f7254f..bca08b3 100644 --- a/fern/pages/openllmetry/tracing/workflows-tasks-agents-tools.mdx +++ b/fern/pages/openllmetry/tracing/workflows-tasks-agents-tools.mdx @@ -275,7 +275,7 @@ In Typescript, you can use the same syntax for async methods. In Python, you’ll need to switch to an equivalent async decorator. So, if you’re decorating an `async` method, use `@aworkflow`, `@atask` and so forth. -See also a separate section on [using threads in Python with OpenLLMetry](/open-ll-metry/tracing/usage-with-threads-python). +See also a separate section on [using threads in Python with OpenLLMetry](/docs/openllmetry/tracing/usage-with-threads-python). ## Decorating Classes (Python only)