Merge pull request #6 from nassimberrada/main

fix broken hyperlinks

docs/api/deploy_router.rst

@@ -89,7 +89,7 @@ explanation. You can detect this and change your policy doing something like:
 Using a custom router
 ---------------------
 
-If you `trained a custom router <https://unify.ai/docs/interfaces/build_router.html>`_, you can deploy it with the Unify API much like using any other endpoint. Assuming we want to deploy the custom router we trained before, we can use the configuration Id in the same API call code to send our prompts to our custom router as follows:
+If you `trained a custom router <https://unify.ai/docs/interfaces/building_router.html>`_, you can deploy it with the Unify API much like using any other endpoint. Assuming we want to deploy the custom router we trained before, we can use the configuration Id in the same API call code to send our prompts to our custom router as follows:
 
 .. code-block:: python
 

docs/api/first_request.rst

@@ -193,7 +193,7 @@ Or **Python**:
     else:
         print(response.text)
 
-The docs for this endpoint are available `here. <https://unify.ai/docs/api/reference.html`_
+The docs for this endpoint are available `here. <https://unify.ai/docs/api/reference.html>`_
 
 Compatible Tools
 ^^^^^^^^^^^^^^^^

docs/concepts/routing.rst

@@ -6,7 +6,7 @@ In this section, you will learn what LLM routing is and how it works.
 What is routing?
 ----------------
 
-In the `benchmarks section <https://unify.ai/docs/concepts/benchmaks.html>`_, we discussed how different models perform better at different tasks, and how appropriate performance benchmarks can help steer and inform model selection for a given use-case. 
+In the `benchmarks section <https://unify.ai/docs/concepts/benchmarks.html>`_, we discussed how different models perform better at different tasks, and how appropriate performance benchmarks can help steer and inform model selection for a given use-case. 
 
 Given the diversity of prompts you can send to an LLM, it can quickly become tedious to manually swap between models for every single prompt, even when they pertain to the same broad category of tasks. 
 
@@ -53,4 +53,4 @@ With runtime routing, your requests are automatically redirected to the provider
 Round Up
 --------
 
-You are now familiar with routing. Next, you can `learn to use the router <htts://unify.ai/docs/api/deploy_router.html>`_, or `build your custom router <https://unify.ai/docs/interfaces/build_router.html>`_.
+You are now familiar with routing. Next, you can `learn to use the router <https://unify.ai/docs/api/deploy_router.html>`_, or `build your custom router <https://unify.ai/docs/interfaces/building_router.html>`_.

docs/interfaces/building_router.rst

@@ -121,4 +121,4 @@ Once saved, the new router view and router configuration are then both visible o
 Round Up
 --------
 
-That’s it! You have now trained your first custom router, ready to be used through our API. You can now `deploy it <https://unify.aid/docs/api/deploy_router.html>`_, or learn `how to query endpoints <https://unify.ai/docs/api/first_request.html>`_ first.
+That’s it! You have now trained your first custom router, ready to be used through our API. You can now `deploy it <https://unify.ai/docs/api/deploy_router.html>`_, or learn `how to query endpoints <https://unify.ai/docs/api/first_request.html>`_ first.

docs/interfaces/connecting_stack.rst

@@ -55,4 +55,4 @@ Once your dataset is uploaded, you can click on it to preview the prompts. For e
 Round Up
 --------
 
-That’s it, you now know how to upload your own endpoints and datasets! You can now `run custom benchmarks <https://unify.ai/docs/interfaces/running_benchmarks.html>`_, `build a custom router <https://unify.ai/docs/interfaces/build_router.html>`_, or `query your endpoint <https://unify.ai/docs/api/first_request.html>`_ with the Unify API. 
+That’s it, you now know how to upload your own endpoints and datasets! You can now `run custom benchmarks <https://unify.ai/docs/interfaces/running_benchmarks.html>`_, `build a custom router <https://unify.ai/docs/interfaces/building_router.html>`_, or `query your endpoint <https://unify.ai/docs/api/first_request.html>`_ with the Unify API. 

docs/interfaces/running_benchmarks.rst

@@ -55,7 +55,7 @@ For granular runtime benchmarks, head to the `benchmarks interface <https://unif
 Each page contains a suite of runtime benchmarks providing timely information on the speed, cost and latency of the endpoints exposed by different endpoint providers. 
 
 .. note::
-    You can learn more about endpoints providers on the dedicated `endpoints <https://unify.ai/docs/concepts/benchmarks.html>`_ section
+    You can learn more about endpoints providers on the dedicated `endpoints <https://unify.ai/docs/concepts/endpoints.html>`_ section
 
 For e.g, the image below corresponds to the benchmark page for :code:`mistral-7b-instruct-v0.2`.