Fix affected snippets after the breaking changes (#164)

integrations/assemblyai.md

@@ -117,6 +117,7 @@ The example below illustrates a generative QA pipeline that seamlessly integrate
 
 ```python
 from haystack import Pipeline
+from haystack.utils import Secret
 from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
 from haystack.components.builders.prompt_builder import PromptBuilder
 from haystack.components.generators import OpenAIGenerator
@@ -133,7 +134,7 @@ Question: {{ question }}
 summary_qa = Pipeline()
 summary_qa.add_component("transcriber", AssemblyAITranscriber(api_key=assemblyai_api_key))
 summary_qa.add_component("prompt_builder", PromptBuilder(template=template))
-summary_qa.add_component("llm", OpenAIGenerator(api_key=openai_api_key, model_name="gpt-3.5-turbo"))
+summary_qa.add_component("llm", OpenAIGenerator(api_key=Secret.from_token("YOUR_OPENAI_API_KEY"), model="gpt-3.5-turbo"))
 summary_qa.connect("transcriber.summarization", "prompt_builder.summary")
 summary_qa.connect("prompt_builder", "llm")
 
@@ -152,6 +153,7 @@ Explore the example below to see how to index speaker diarization information an
 ```python 
 from haystack.document_stores.in_memory import InMemoryDocumentStore
 from haystack import Pipeline
+from haystack.utils import Secret
 from haystack.components.retrievers.in_memory import InMemoryBM25Retriever
 from haystack.components.builders.prompt_builder import PromptBuilder
 from haystack.components.generators import OpenAIGenerator
@@ -176,7 +178,7 @@ Question: {{ question }}
 pipe = Pipeline()
 pipe.add_component("retriever", InMemoryBM25Retriever(document_store=document_store, top_k=3))
 pipe.add_component("prompt_builder", PromptBuilder(template=template))
-pipe.add_component("llm", OpenAIGenerator(api_key=openai_api_key, model_name="gpt-3.5-turbo"))
+pipe.add_component("llm", OpenAIGenerator(api_key=Secret.from_token("YOUR_OPENAI_API_KEY"), model="gpt-3.5-turbo"))
 
 pipe.connect("retriever", "prompt_builder.documents")
 pipe.connect("prompt_builder", "llm")

integrations/huggingface.md

@@ -80,6 +80,7 @@ Below is the example query pipeline that uses `mistralai/Mistral-7B-v0.1` hosted
 
 ```python
 from haystack import Pipeline
+from haystack.utils import Secret
 from haystack.components.retrievers.in_memory import InMemoryBM25Retriever
 from haystack.components.builders.prompt_builder import PromptBuilder
 from haystack.components.generators import HuggingFaceTGIGenerator
@@ -98,7 +99,7 @@ pipe = Pipeline()
 
 pipe.add_component("retriever", InMemoryBM25Retriever(document_store=docstore))
 pipe.add_component("prompt_builder", PromptBuilder(template=template))
-pipe.add_component("llm", HuggingFaceTGIGenerator(model="mistralai/Mistral-7B-v0.1", token="HF_TOKEN"))
+pipe.add_component("llm", HuggingFaceTGIGenerator(model="mistralai/Mistral-7B-v0.1", token=Secret.from_token("YOUR_HF_API_TOKEN")))
 pipe.connect("retriever", "prompt_builder.documents")
 pipe.connect("prompt_builder", "llm")
 

integrations/instructor-embedder.md

@@ -183,7 +183,7 @@ indexing_pipeline.add_component(
     instance=DocumentWriter(document_store=doc_store), name="DocWriter"
 )
 # Connect the output of DocEmbedder to the input of DocWriter
-indexing_pipeline.connect(connect_from="DocEmbedder", connect_to="DocWriter")
+indexing_pipeline.connect("DocEmbedder", "DocWriter")
 
 # Load the 'XSum' dataset from HuggingFace (https://huggingface.co/datasets/xsum)
 dataset = load_dataset("xsum", split="train")

integrations/llama_cpp.md

@@ -221,7 +221,7 @@ doc_embedder = SentenceTransformersDocumentEmbedder(model="sentence-transformers
 indexing_pipeline = Pipeline()
 indexing_pipeline.add_component(instance=doc_embedder, name="DocEmbedder")
 indexing_pipeline.add_component(instance=DocumentWriter(document_store=doc_store), name="DocWriter")
-indexing_pipeline.connect(connect_from="DocEmbedder", connect_to="DocWriter")
+indexing_pipeline.connect("DocEmbedder", "DocWriter")
 
 indexing_pipeline.run({"DocEmbedder": {"documents": docs}})
 ```

integrations/lmformatenforcer.md

@@ -109,7 +109,7 @@ schema_json_str = AnswerFormat.schema_json()
 prompt = f'{question}{schema_json_str}'
 
 
-model = HuggingFaceLocalGenerator(model_name_or_path="meta-llama/Llama-2-7b-chat-hf")
+model = HuggingFaceLocalGenerator(model="meta-llama/Llama-2-7b-chat-hf")
 format_enforcer = LMFormatEnforcerLocalGenerator(model, character_level_parser)
 pipeline = Pipeline()
 pipeline.add_component(instance=format_enforcer, name='model')

integrations/mastodon-fetcher.md

@@ -52,12 +52,13 @@ mastodon_fetcher.run(username="[email protected]")
 
 ```python
 from haystack import Pipeline
+from haystack.utils import Secret
 from mastodon_fetcher_haystack.mastodon_fetcher import MastodonFetcher
 from haystack.components.generators import OpenAIGenerator
 from haystack.components.builders import PromptBuilder
 
 prompt_builder = PromptBuilder(template='YOUR_PROMPT_TEMPLATE')
-llm = OpenAIGenerator(api_key'YOUR_OPENAI_API_KEY')
+llm = OpenAIGenerator(api_key=Secret.from_token("YOUR_OPENAI_API_KEY"))
 
 pipe = Pipeline()
 pipe.add_component("fetcher", mastodon_fetcher)

integrations/openai.md

@@ -50,6 +50,7 @@ Below is the example indexing pipeline with `InMemoryDocumentStore`, `OpenAIDocu
 
 ```python
 from haystack import Document, Pipeline
+from haystack.utils import Secret
 from haystack.document_stores.in_memory import InMemoryDocumentStore
 from haystack.components.embedders import OpenAIDocumentEmbedder
 from haystack.components.writers import DocumentWriter
@@ -61,7 +62,7 @@ documents = [Document(content="My name is Wolfgang and I live in Berlin"),
              Document(content="Germany has many big cities")]
 
 indexing_pipeline = Pipeline()
-indexing_pipeline.add_component("embedder", OpenAIDocumentEmbedder(api_key="OPENAI_API_KEY", model="text-embedding-ada-002"))
+indexing_pipeline.add_component("embedder", OpenAIDocumentEmbedder(api_key=Secret.from_token("YOUR_OPENAI_API_KEY"), model="text-embedding-ada-002"))
 indexing_pipeline.add_component("writer", DocumentWriter(document_store=document_store))
 indexing_pipeline.connect("embedder", "writer")
 
@@ -70,17 +71,18 @@ indexing_pipeline.run({"embedder": {"documents": documents}})
 
 #### Generative Models (LLMs)
 
-You can leverage OpenAI models through two components: [GPTGenerator](https://docs.haystack.deepset.ai/v2.0/docs/gptgenerator) and [GPTChatGenerator](https://docs.haystack.deepset.ai/v2.0/docs/gptchatgenerator).
+You can leverage OpenAI models through two components: [OpenAIGenerator](https://docs.haystack.deepset.ai/v2.0/docs/openaigenerator) and [OpenAIChatGenerator](https://docs.haystack.deepset.ai/v2.0/docs/openaichatgenerator).
 
-To use OpenAI's GPT models for text generation, initialize a `GPTGenerator` with the model name and OpenAI API key. You can then use the `GPTGenerator` instance in a question answering pipeline after the `PromptBuilder`.  
+To use OpenAI's GPT models for text generation, initialize a `OpenAIGenerator` with the model name and OpenAI API key. You can then use the `OpenAIGenerator` instance in a question answering pipeline after the `PromptBuilder`.  
 
-Below is the example of generative questions answering pipeline using RAG with `PromptBuilder` and  `GPTGenerator`:
+Below is the example of generative questions answering pipeline using RAG with `PromptBuilder` and  `OpenAIGenerator`:
 
 ```python
 from haystack import Pipeline
+from haystack.utils import Secret
 from haystack.components.retrievers.in_memory import InMemoryBM25Retriever
 from haystack.components.builders.prompt_builder import PromptBuilder
-from haystack.components.generators import GPTGenerator
+from haystack.components.generators import OpenAIGenerator
 
 template = """
 Given the following information, answer the question.
@@ -96,7 +98,7 @@ pipe = Pipeline()
 
 pipe.add_component("retriever", InMemoryBM25Retriever(document_store=document_store))
 pipe.add_component("prompt_builder", PromptBuilder(template=template))
-pipe.add_component("llm", GPTGenerator(model="gpt-4", api_key="OPENAI_API_KEY"))
+pipe.add_component("llm", OpenAIGenerator(model="gpt-4", api_key=Secret.from_token("YOUR_OPENAI_API_KEY")))
 pipe.connect("retriever", "prompt_builder.documents")
 pipe.connect("prompt_builder", "llm")
 

integrations/pinecone-document-store.md

@@ -101,6 +101,7 @@ indexing.run({"converter": {"sources": ["filename.md"]}})
 Once you have documents in your `PineconeDocumentStore`, it's ready to be used in any Haystack pipeline. Then, you can use `PineconeDenseRetriever` to retrieve data from your PineconeDocumentStore. For example, below is a pipeline that makes use of a custom prompt that is designed to answer questions for the retrieved documents.
 
 ```python
+from haystack.utils import Secret
 from haystack.components.embedders import SentenceTransformersTextEmbedder
 from haystack.components.builders import PromptBuilder
 from haystack.components.generators import OpenAIGenerator
@@ -125,7 +126,7 @@ query_pipeline = Pipeline()
 query_pipeline.add_component("text_embedder", SentenceTransformersTextEmbedder())
 query_pipeline.add_component("retriever", PineconeDenseRetriever(document_store=document_store))
 query_pipeline.add_component("prompt_builder", PromptBuilder(template=prompt_template))
-query_pipeline.add_component("generator", OpenAIGenerator(api_key=YOUR_OPENAI_KEY, model="gpt-4"))
+query_pipeline.add_component("generator", OpenAIGenerator(api_key=Secret.from_token("YOUR_OPENAI_API_KEY"), model="gpt-4"))
 query_pipeline.connect("text_embedder.embedding", "retriever.query_embedding")
 query_pipeline.connect("retriever.documents", "prompt_builder.documents")
 query_pipeline.connect("prompt_builder", "generator")

integrations/voyage.md

@@ -97,7 +97,7 @@ doc_embedder = VoyageDocumentEmbedder(
 indexing_pipeline = Pipeline()
 indexing_pipeline.add_component(instance=doc_embedder, name="DocEmbedder")
 indexing_pipeline.add_component(instance=DocumentWriter(document_store=doc_store), name="DocWriter")
-indexing_pipeline.connect(connect_from="DocEmbedder", connect_to="DocWriter")
+indexing_pipeline.connect("DocEmbedder", "DocWriter")
 
 indexing_pipeline.run({"DocEmbedder": {"documents": docs}})