Update URLs (#206)

* update URLs

* make 2.0 URLs future-proof

* fix typos (#207)

README.md

@@ -6,7 +6,7 @@ These integrations are maintained by their respective owner or authors. You can
 
 ## What are Haystack Integrations?
 
-Haystack Integrations are a Document Store, Model Provider, Custom Component, Monitoring Tool or Evaluation Framework that are either external packages or additional technologies that can be used with Haystack. Some integrations may be maintained by the deepset team, others are community contributions owned by the authors of the integration. Read more about Haystack Integrations in [Introduction to Integrations](https://docs.haystack.deepset.ai/v2.0/docs/integrations).
+Haystack Integrations are a Document Store, Model Provider, Custom Component, Monitoring Tool or Evaluation Framework that are either external packages or additional technologies that can be used with Haystack. Some integrations may be maintained by the deepset team, others are community contributions owned by the authors of the integration. Read more about Haystack Integrations in [Introduction to Integrations](https://docs.haystack.deepset.ai/docs/integrations).
 
 ## Looking for prompts?
 

integrations/amazon-bedrock.md

@@ -38,12 +38,12 @@ pip install amazon-bedrock-haystack
 
 ## Usage
 
-Once installed, you will have access to [AmazonBedrockGenerator](https://docs.haystack.deepset.ai/v2.0/docs/amazonbedrockgenerator) and [AmazonBedrockChatGenerator](https://docs.haystack.deepset.ai/v2.0/docs/amazonbedrockchatgenerator) components that support generative language models on Amazon Bedrock.
-You will also have access to the [AmazonBedrockTextEmbedder](https://docs.haystack.deepset.ai/v2.0/docs/amazonbedrocktextembedder) and [AmazonBedrockDocumentEmbedder](https://docs.haystack.deepset.ai/v2.0/docs/amazonbedrockdocumentembedder), which can be used to compute embeddings.
+Once installed, you will have access to [AmazonBedrockGenerator](https://docs.haystack.deepset.ai/docs/amazonbedrockgenerator) and [AmazonBedrockChatGenerator](https://docs.haystack.deepset.ai/docs/amazonbedrockchatgenerator) components that support generative language models on Amazon Bedrock.
+You will also have access to the [AmazonBedrockTextEmbedder](https://docs.haystack.deepset.ai/docs/amazonbedrocktextembedder) and [AmazonBedrockDocumentEmbedder](https://docs.haystack.deepset.ai/docs/amazonbedrockdocumentembedder), which can be used to compute embeddings.
 
 ### AmazonBedrockGenerator
 
-To use this integration for text generation, initialize an `AmazonBedrockGenerator` with the model name, the AWS credentials (`AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, `AWS_DEFAULT_REGION`) should be set as environment variables or passed as [Secret](https://docs.haystack.deepset.ai/v2.0/docs/secret-management) arguments. 
+To use this integration for text generation, initialize an `AmazonBedrockGenerator` with the model name, the AWS credentials (`AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, `AWS_DEFAULT_REGION`) should be set as environment variables or passed as [Secret](https://docs.haystack.deepset.ai/docs/secret-management) arguments. 
 Note, make sure the region you set supports Amazon Bedrock. 
 
 Currently, the following models are supported: 

integrations/amazon-sagemaker.md

@@ -31,7 +31,7 @@ toc: true
 
 [Amazon Sagemaker](https://docs.aws.amazon.com/sagemaker/latest/dg/whatis.html) is a comprehensive, fully managed machine learning service 
 that allows data scientists and developers to build, train, and deploy ML models efficiently. More information can be found on the 
-[documentation page](https://docs.haystack.deepset.ai/v2.0/docs/sagemakergenerator).
+[documentation page](https://docs.haystack.deepset.ai/docs/sagemakergenerator).
 
 ## Haystack 2.x
 
@@ -44,7 +44,7 @@ pip install amazon-sagemaker-haystack
 
 ### Usage
 
-Once installed, you will have access to a [SagemakerGenerator](https://docs.haystack.deepset.ai/v2.0/docs/sagemakergenerator) that supports models from various providers. To know more
+Once installed, you will have access to a [SagemakerGenerator](https://docs.haystack.deepset.ai/docs/sagemakergenerator) that supports models from various providers. To know more
 about which models are supported, check out [Sagemaker's documentation](https://docs.aws.amazon.com/sagemaker/latest/dg/jumpstart-foundation-models.html).
 
 To use this integration for text generation, initialize a `SagemakerGenerator` with the model name and aws credentials: 

integrations/anthropic.md

@@ -15,7 +15,7 @@ report_issue: https://github.com/deepset-ai/haystack/issues
 logo: /logos/anthropic.png
 ---
 
-You can use [Anhtropic Claude](https://docs.anthropic.com/claude/reference/getting-started-with-the-api) in your Haystack pipelines with the [PromptNode](https://docs.haystack.deepset.ai/docs/prompt_node#using-anthropic-generative-models), which can also be used with and [Agent](https://docs.haystack.deepset.ai/docs/agent).
+You can use [Anhtropic Claude](https://docs.anthropic.com/claude/reference/getting-started-with-the-api) in your Haystack pipelines with the [PromptNode](https://docs.haystack.deepset.ai/v1.25/docs/prompt_node#using-anthropic-generative-models), which can also be used with and [Agent](https://docs.haystack.deepset.ai/v1.25/docs/agent).
 
 ## Installation
 

integrations/astradb.md

@@ -37,8 +37,8 @@ This integration allows you to use AstraDB for document storage and retrieval in
 
 ## Components
 
-- [`AstraDocumentStore`](https://docs.haystack.deepset.ai/v2.0/docs/astradocumentstore). This component serves as a persistent data store for your Haystack documents, and supports a number of embedding models and vector dimensions.
-- [`AstraEmbeddingRetriever`](https://docs.haystack.deepset.ai/v2.0/docs/astraretriever) This is an embedding-based Retriever compatible with the Astra Document Store.
+- [`AstraDocumentStore`](https://docs.haystack.deepset.ai/docs/astradocumentstore). This component serves as a persistent data store for your Haystack documents, and supports a number of embedding models and vector dimensions.
+- [`AstraEmbeddingRetriever`](https://docs.haystack.deepset.ai/docs/astraretriever) This is an embedding-based Retriever compatible with the Astra Document Store.
 
 
 ## Initialization

integrations/azure.md

@@ -44,16 +44,16 @@ To work with Azure components, you will need an Azure OpenAI API key, an [Azure
 
 ### Components
 
-- [AzureOpenAIGenerator](https://docs.haystack.deepset.ai/v2.0/docs/azureopenaigenerator)
-- [AzureOpenAIChatGenerator](https://docs.haystack.deepset.ai/v2.0/docs/azureopenaichatgenerator)
-- [AzureOpenAITextEmbedder](https://docs.haystack.deepset.ai/v2.0/docs/azureopenaitextembedder)
-- [AzureOpenAIDocumentEmbedder](https://docs.haystack.deepset.ai/v2.0/docs/azureopenaidocumentembedder)
+- [AzureOpenAIGenerator](https://docs.haystack.deepset.ai/docs/azureopenaigenerator)
+- [AzureOpenAIChatGenerator](https://docs.haystack.deepset.ai/docs/azureopenaichatgenerator)
+- [AzureOpenAITextEmbedder](https://docs.haystack.deepset.ai/docs/azureopenaitextembedder)
+- [AzureOpenAIDocumentEmbedder](https://docs.haystack.deepset.ai/docs/azureopenaidocumentembedder)
 
-All components use `AZURE_OPENAI_API_KEY` and `AZURE_OPENAI_AD_TOKEN` environment variables by default. Otherwise, you can pass `api_key` and `azure_ad_token` at initialization using `Secret` class. Read more about [Secret Handling](https://docs.haystack.deepset.ai/v2.0/docs/secret-management#structured-secret-handling).
+All components use `AZURE_OPENAI_API_KEY` and `AZURE_OPENAI_AD_TOKEN` environment variables by default. Otherwise, you can pass `api_key` and `azure_ad_token` at initialization using `Secret` class. Read more about [Secret Handling](https://docs.haystack.deepset.ai/docs/secret-management#structured-secret-handling).
 
 ### Embedding Models
 
-You can leverage embedding models from Azure OpenAI through two components: [AzureOpenAITextEmbedder](https://docs.haystack.deepset.ai/v2.0/docs/azureopenaitextembedder) and [AzureOpenAIDocumentEmbedder](https://docs.haystack.deepset.ai/v2.0/docs/azureopenaidocumentembedder).
+You can leverage embedding models from Azure OpenAI through two components: [AzureOpenAITextEmbedder](https://docs.haystack.deepset.ai/docs/azureopenaitextembedder) and [AzureOpenAIDocumentEmbedder](https://docs.haystack.deepset.ai/docs/azureopenaidocumentembedder).
 
 To create semantic embeddings for documents, use `AzureOpenAIDocumentEmbedder` in your indexing pipeline. For generating embeddings for queries, use `AzureOpenAITextEmbedder`. Once you've selected the suitable component for your specific use case, initialize the component with required parameters.
 
@@ -84,7 +84,7 @@ indexing_pipeline.run({"embedder": {"documents": documents}})
 
 ### Generative Models (LLMs)
 
-You can leverage Azure OpenAI models through two components: [AzureOpenAIGenerator](https://docs.haystack.deepset.ai/v2.0/docs/azureopenaigenerator) and [AzureOpenAIChatGenerator](https://docs.haystack.deepset.ai/v2.0/docs/azureopenaichatgenerator).
+You can leverage Azure OpenAI models through two components: [AzureOpenAIGenerator](https://docs.haystack.deepset.ai/docs/azureopenaigenerator) and [AzureOpenAIChatGenerator](https://docs.haystack.deepset.ai/docs/azureopenaichatgenerator).
 
 To use OpenAI models deployed through Azure services for text generation, initialize a `AzureOpenAIGenerator` with `azure_deployment` and `azure_endpoint`. You can then use the `AzureOpenAIGenerator` instance in a pipeline after the `PromptBuilder`.  
 

integrations/cohere.md

@@ -33,7 +33,7 @@ toc: true
 
 ## Haystack 2.0
 
-You can use [Cohere Models](https://cohere.com/) in your Haystack 2.0 pipelines with the [Generators](https://docs.haystack.deepset.ai/v2.0/docs/generators) and [Embedders](https://docs.haystack.deepset.ai/v2.0/docs/embedders).
+You can use [Cohere Models](https://cohere.com/) in your Haystack 2.0 pipelines with the [Generators](https://docs.haystack.deepset.ai/docs/generators) and [Embedders](https://docs.haystack.deepset.ai/docs/embedders).
 
 ### Installation
 
@@ -47,7 +47,7 @@ You can use Cohere models in various ways:
 
 #### Embedding Models
 
-You can leverage `/embed` models from Cohere through two components: [CohereTextEmbedder](https://docs.haystack.deepset.ai/v2.0/docs/coheretextembedder) and [CohereDocumentEmbedder](https://docs.haystack.deepset.ai/v2.0/docs/coheredocumentembedder). These components support both **Embed v2** and **Embed v3** models.
+You can leverage `/embed` models from Cohere through two components: [CohereTextEmbedder](https://docs.haystack.deepset.ai/docs/coheretextembedder) and [CohereDocumentEmbedder](https://docs.haystack.deepset.ai/docs/coheredocumentembedder). These components support both **Embed v2** and **Embed v3** models.
 
 To create semantic embeddings for documents, use `CohereDocumentEmbedder` in your indexing pipeline. For generating embeddings for queries, use `CohereTextEmbedder`. Once you've selected the suitable component for your specific use case, initialize the component with the model name. By default, the Cohere API key with be automatically read from either the `COHERE_API_KEY` environment variable or the `CO_API_KEY` environment variable.
 
@@ -76,7 +76,7 @@ indexing_pipeline.run({"embedder": {"documents": documents}})
 
 #### Generative Models (LLMs)
 
-To use `/generate` models from Cohere, initialize a [CohereGenerator](https://docs.haystack.deepset.ai/v2.0/docs/coheregenerator) with the model name. By default, the Cohere API key with be automatically read from either the `COHERE_API_KEY` environment variable or the `CO_API_KEY` environment variable. You can then use this `CohereGenerator` in a question answering pipeline after the `PromptBuilder`.
+To use `/generate` models from Cohere, initialize a [CohereGenerator](https://docs.haystack.deepset.ai/docs/coheregenerator) with the model name. By default, the Cohere API key with be automatically read from either the `COHERE_API_KEY` environment variable or the `CO_API_KEY` environment variable. You can then use this `CohereGenerator` in a question answering pipeline after the `PromptBuilder`.
 
 Below is the example of generative questions answering pipeline using RAG with `PromptBuilder` and `CohereGenerator`:
 
@@ -112,7 +112,7 @@ pipe.run({
 })
 ```
 
-Similar to the above example, you can also use [`CohereChatGenerator`](https://docs.haystack.deepset.ai/v2.0/docs/coherechatgenerator) to use Cohere `/chat` models and features (streaming, connectors) in your pipeline.
+Similar to the above example, you can also use [`CohereChatGenerator`](https://docs.haystack.deepset.ai/docs/coherechatgenerator) to use Cohere `/chat` models and features (streaming, connectors) in your pipeline.
 
 ```python
 from haystack import Pipeline
@@ -136,7 +136,7 @@ print(res)
 
 ## Haystack 1.x
 
-You can use [Cohere Models](https://cohere.com/) in your Haystack pipelines with the [EmbeddingRetriever](https://docs.haystack.deepset.ai/docs/retriever#embedding-retrieval-recommended), [PromptNode](https://docs.haystack.deepset.ai/docs/prompt_node), and [CohereRanker](https://docs.haystack.deepset.ai/docs/ranker#cohereranker).
+You can use [Cohere Models](https://cohere.com/) in your Haystack pipelines with the [EmbeddingRetriever](https://docs.haystack.deepset.ai/v1.25/docs/retriever#embedding-retrieval-recommended), [PromptNode](https://docs.haystack.deepset.ai/v1.25/docs/prompt_node), and [CohereRanker](https://docs.haystack.deepset.ai/v1.25/docs/ranker#cohereranker).
 
 ### Installation (1.x)
 

integrations/context-ai.md

@@ -85,7 +85,7 @@ pipe.connect("prompt_builder.prompt", "llm.messages")
 pipe.connect("prompt_builder.prompt", "prompt_analytics")
 pipe.connect("llm.replies", "assistant_analytics")
 
-# thread_id is unqiue to each conversation
+# thread_id is unique to each conversation
 context_parameters = {"thread_id": uuid.uuid4(), "metadata": {"model": model, "user_id": "1234"}}
 location = "Berlin"
 messages = [ChatMessage.from_system("Always respond in German even if some input data is in other languages."),

integrations/deepeval.md

@@ -26,7 +26,7 @@ toc: true
 
 ## Overview
 
-[DeepEval](https://github.com/confident-ai/deepeval) (by [Confident AI](https://www.confident-ai.com/)) is an open source framework for model-based evaluation to evaluate your LLM applications by quantifying their performance on aspects such as faithfulness, answer relevancy, contextual recall etc. More information can be found on the [documentation page](https://docs.haystack.deepset.ai/v2.0/docs/deepevalevaluator).
+[DeepEval](https://github.com/confident-ai/deepeval) (by [Confident AI](https://www.confident-ai.com/)) is an open source framework for model-based evaluation to evaluate your LLM applications by quantifying their performance on aspects such as faithfulness, answer relevancy, contextual recall etc. More information can be found on the [documentation page](https://docs.haystack.deepset.ai/docs/deepevalevaluator).
 
 ## Installation
 
@@ -37,7 +37,7 @@ pip install deepeval-haystack
 
 ## Usage
 
-Once installed, you will have access to a [DeepEvalEvaluator](https://docs.haystack.deepset.ai/v2.0/docs/deepevalevaluator) that supports a variety of model-based evaluation metrics: 
+Once installed, you will have access to a [DeepEvalEvaluator](https://docs.haystack.deepset.ai/docs/deepevalevaluator) that supports a variety of model-based evaluation metrics: 
 - Answer Relevancy
 - Faithfulness
 - Contextual Precision