merge

wandb · Aug 7, 2024 · 9e83a28 · 9e83a28
2 parents 2194d93 + 73ad0cc
commit 9e83a28
Show file tree

Hide file tree

Showing 211 changed files with 4,921 additions and 1,920 deletions.
diff --git a/docs/docs/guides/core-types/datasets.md b/docs/docs/guides/core-types/datasets.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 2
-hide_table_of_contents: true
----
-
 # Datasets
 
 `Dataset`s enable you to collect examples for evaluation and automatically track versions for accurate comparisons. Use this to download the latest version locally with a simple API.

diff --git a/docs/docs/guides/core-types/evaluations.md b/docs/docs/guides/core-types/evaluations.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 4
-hide_table_of_contents: true
----
-
 # Evaluation
 
 Evaluation-driven development helps you reliably iterate on an application. The `Evaluation` class is designed to assess the performance of a `Model` on a given `Dataset` or set of examples using scoring functions.

diff --git a/docs/docs/guides/core-types/models.md b/docs/docs/guides/core-types/models.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 3
-hide_table_of_contents: true
----
-
 # Models
 
 A `Model` is a combination of data (which can include configuration, trained model weights, or other information) and code that defines how the model operates. By structuring your code to be compatible with this API, you benefit from a structured way to version your application so you can more systematically keep track of your experiments.

diff --git a/docs/docs/guides/integrations/anthropic.md b/docs/docs/guides/integrations/anthropic.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 1
-hide_table_of_contents: true
----
-
 # Anthropic
 
 Weave automatically tracks and logs LLM calls made via the [Anthropic Python library](https://github.com/anthropics/anthropic-sdk-python), after `weave.init()` is called.

diff --git a/docs/docs/guides/integrations/cohere.md b/docs/docs/guides/integrations/cohere.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 1
-hide_table_of_contents: true
----
-
 # Cohere
 
 Weave automatically tracks and logs LLM calls made via the [Cohere Python library](https://github.com/cohere-ai/cohere-python) after `weave.init()` is called.

diff --git a/docs/docs/guides/integrations/dspy.md b/docs/docs/guides/integrations/dspy.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 2
-hide_table_of_contents: true
----
-
 # DSPy
 
 [DSPy](https://dspy-docs.vercel.app/) is a framework for algorithmically optimizing LM prompts and weights, especially when LMs are used one or more times within a pipeline. Weave automatically tracks and logs calls made using DSPy modules and functions.

diff --git a/docs/docs/guides/integrations/google-gemini.md b/docs/docs/guides/integrations/google-gemini.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 1
-hide_table_of_contents: true
----
-
 # Google Gemini
 
 Google offers two ways of calling Gemini via API:

diff --git a/docs/docs/guides/integrations/groq.md b/docs/docs/guides/integrations/groq.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 2
-hide_table_of_contents: true
----
-
 # Groq
 
 [Groq](https://groq.com/) is the AI infrastructure company that delivers fast AI inference. The LPU™ Inference Engine by Groq is a hardware and software platform that delivers exceptional compute speed, quality, and energy efficiency. Weave automatically tracks and logs calls made using Groq chat completion calls.

diff --git a/docs/docs/guides/integrations/langchain.md b/docs/docs/guides/integrations/langchain.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 2
-hide_table_of_contents: true
----
-
 # LangChain
 
 Weave is designed to make tracking and logging all calls made through the [LangChain Python library](https://github.com/langchain-ai/langchain) effortless.

diff --git a/docs/docs/guides/integrations/litellm.md b/docs/docs/guides/integrations/litellm.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 1
-hide_table_of_contents: true
----
-
 # LiteLLM
 
 Weave automatically tracks and logs LLM calls made via LiteLLM, after `weave.init()` is called.

diff --git a/docs/docs/guides/integrations/llamaindex.md b/docs/docs/guides/integrations/llamaindex.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 0
-hide_table_of_contents: true
----
-
 # LlamaIndex
 
 Weave is designed to simplify the tracking and logging of all calls made through the [LlamaIndex Python library](https://github.com/run-llama/llama_index).

diff --git a/docs/docs/guides/integrations/local_models.md b/docs/docs/guides/integrations/local_models.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 0
-hide_table_of_contents: true
----
-
 # Local Models
 
 Many developers download and run open source models like LLama-3, Mixtral, Gemma, Phi and more locally. There are quite a few ways of running these models locally and Weave supports a few of them out of the box, as long as they support OpenAI SDK compatibility.

diff --git a/docs/docs/guides/integrations/mistral.md b/docs/docs/guides/integrations/mistral.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 1
-hide_table_of_contents: true
----
-
 # MistralAI
 
 Weave automatically tracks and logs LLM calls made via the [MistralAI Python library](https://github.com/mistralai/client-python).

diff --git a/docs/docs/guides/integrations/openai.md b/docs/docs/guides/integrations/openai.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 0
-hide_table_of_contents: true
----
-
 # OpenAI
 
 ## Tracing

diff --git a/docs/docs/guides/integrations/openrouter.md b/docs/docs/guides/integrations/openrouter.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 1
-hide_table_of_contents: true
----
-
 # Open Router
 
 Openrouter.ai is a unified interface for many LLMs, supporting both foundational models like OpenAI GPT-4, Anthropic Claude, Google Gemini but also open source models like LLama-3, Mixtral and [many more](https://openrouter.ai/models), some models are even offered for free. 
@@ -47,4 +42,4 @@ response = chat_completion.choices[0].message.content
 print("Model response:\n", response)
 ```
 
-While this is a simple example to get started, see our [OpenAI](/guides/integrations/openai#track-your-own-ops) guide for more details on how to integrate Weave with your own functions for more complex use cases.
+While this is a simple example to get started, see our [OpenAI](/guides/integrations/openai#track-your-own-ops) guide for more details on how to integrate Weave with your own functions for more complex use cases.
diff --git a/docs/docs/guides/integrations/together_ai.md b/docs/docs/guides/integrations/together_ai.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 0
-hide_table_of_contents: true
----
-
 # Together AI
 
 Together AI is a platform for building and finetuning generative AI models, focusing on Open Source LLMs, and allowing customers to fine-tune and host their own models.

diff --git a/docs/docs/guides/tools/deploy.md b/docs/docs/guides/tools/deploy.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 1
-hide_table_of_contents: true
----
-
 # Deploy
 
 ## Deploy to GCP

diff --git a/docs/docs/guides/tools/serve.md b/docs/docs/guides/tools/serve.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 0
-hide_table_of_contents: true
----
-
 # Serve
 
 Given a Weave ref to any Weave Model you can run:

diff --git a/docs/docs/guides/tracking/feedback.md b/docs/docs/guides/tracking/feedback.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 3
-hide_table_of_contents: true
----
-
 # Feedback
 
 Evaluating LLM applications automatically is challenging. Teams often rely on direct user feedback, particularly from domain experts, who assess the content quality using simple indicators such as thumbs up or down. Developers also actively identify and resolve content issues.

diff --git a/docs/docs/guides/tracking/objects.md b/docs/docs/guides/tracking/objects.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 0
-hide_table_of_contents: true
----
-
 # Objects
 
 Weave's serialization layer saves and versions Python objects.

diff --git a/docs/docs/guides/tracking/ops.md b/docs/docs/guides/tracking/ops.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 1
-hide_table_of_contents: true
----
-
 # Ops
 
 A Weave op is a versioned function that automatically logs all calls.

diff --git a/docs/docs/guides/tracking/tracing.md b/docs/docs/guides/tracking/tracing.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 2
-hide_table_of_contents: true
----
-
 # Tracing
 
 Tracing is a powerful feature in Weave that allows you to track the inputs and outputs of functions seamlessly. Follow these steps to get started:

diff --git a/docs/docs/introduction.md b/docs/docs/introduction.md
@@ -1,7 +1,5 @@
 ---
 slug: /
-sidebar_position: 1
-hide_table_of_contents: true
 ---
 
 # Introduction

diff --git a/docs/docs/quickstart.md b/docs/docs/quickstart.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 1
-hide_table_of_contents: true
----
-
 # Track LLM inputs & outputs
 
 <!-- TODO: Update wandb.me/weave-quickstart to match this new link -->

diff --git a/docs/docs/tutorial-eval.md b/docs/docs/tutorial-eval.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 2
-hide_table_of_contents: true
----
-
 # Tutorial: Build an Evaluation pipeline
 
 To iterate on an application, we need a way to evaluate if it's improving. To do so, a common practice is to test it against the same set of examples when there is a change. Weave has a first-class way to track evaluations with `Model` & `Evaluation` classes. We have built the APIs to make minimal assumptions to allow for the flexibility to support a wide array of use-cases.

diff --git a/docs/docs/tutorial-rag.md b/docs/docs/tutorial-rag.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 3
-hide_table_of_contents: true
----
-
 # Tutorial: Model-Based Evaluation of RAG applications
 
 Retrieval Augmented Generation (RAG) is a common way of building Generative AI applications that have access to custom knowledge bases. 

diff --git a/docs/docs/tutorial-tracing_2.md b/docs/docs/tutorial-tracing_2.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 1
-hide_table_of_contents: true
----
-
 # Track data flows and app metadata
 
 In the [Track LLM inputs & outputs](/quickstart) tutorial, the basics of tracking the inputs and outputs of your LLMs was covered.

diff --git a/docs/docs/tutorial-weave_models.md b/docs/docs/tutorial-weave_models.md
@@ -1,8 +1,3 @@
----
-sidebar_position: 1
-hide_table_of_contents: true
----
-
 # App versioning
 
 Tracking the [inputs, outputs, metadata](/quickstart) as well as [data flowing through your app](/tutorial-tracing_2) is critical to understanding the performance of your system. However **versioning your app over time** is also critical to understand how modifications to your code or app attributes change your outputs. Weave's `Model` class is how these changes can be tracked in Weave. 

diff --git a/docs/docs_old/CONTRIBUTING.md b/docs/docs_old/CONTRIBUTING.md
diff --git a/docs/docs_old/INSTALLATION.md b/docs/docs_old/INSTALLATION.md