migration.mdx
1 --- 2 title: "Migration Guide" 3 id: migration 4 slug: "/migration" 5 description: "Learn how to make the move to Haystack 2.x from Haystack 1.x." 6 --- 7 8 # Migration Guide 9 10 Learn how to make the move to Haystack 2.x from Haystack 1.x. 11 12 This guide is designed for those with previous experience with Haystack and who are interested in understanding the differences between Haystack 1.x and Haystack 2.x. If you're new to Haystack, skip this page and proceed directly to Haystack 2.x [documentation](get-started.mdx). 13 14 ## Major Changes 15 16 Haystack 2.x represents a significant overhaul of Haystack 1.x, and it's important to note that certain key concepts outlined in this section don't have a direct correlation between the two versions. 17 18 ### Package Name 19 20 Haystack 1.x was distributed with a package called `farm-haystack`. To migrate your application, you must uninstall `farm-haystack` and install the new `haystack-ai` package for Haystack 2.x. 21 22 :::warning 23 Two versions of the project cannot coexist in the same Python environment. 24 25 One of the options is to remove both packages if they are installed in the same environment, followed by installing only one of them: 26 27 ```bash 28 pip uninstall -y farm-haystack haystack-ai 29 pip install haystack-ai 30 ``` 31 ::: 32 33 ### Nodes 34 35 While Haystack 2.x continues to rely on the `Pipeline` abstraction, the elements linked in a pipeline graph are now referred to as just _components_, replacing the terms _nodes_ and _pipeline components_ used in the previous versions. The [_Migrating Components_](#migrating-components) paragraph below outlines which component in Haystack 2.x can be used as a replacement for a specific 1.x node. 36 37 ### Pipelines 38 39 Pipelines continue to serve as the fundamental structure of all Haystack applications. While the concept of `Pipeline` abstraction remains consistent, Haystack 2.x introduces significant enhancements that address various limitations of its predecessor. For instance, the pipelines now support loops. Pipelines also offer greater flexibility in their input, which is no longer restricted to queries. The pipeline now allows to route the output of a component to multiple recipients. This increases flexibility, however, comes with notable differences in the pipeline definition process in Haystack 2.x compared to the previous version. 40 41 In Haystack 1.x, a pipeline was built by adding one node after the other. In the resulting pipeline graph, edges are automatically added to connect those nodes in the order they were added. 42 43 Building a pipeline in Haystack 2.x is a two-step process: 44 45 1. Initially, components are added to the pipeline without any specific order by calling the `add_component` method. 46 2. Subsequently, the components must be explicitly connected by calling the `connect` method to define the final graph. 47 48 To migrate an existing pipeline, the first step is to go through the nodes and identify their counterparts in Haystack 2.x (see the following section, [_Migrating Components_](#migrating-components), for guidance). If all the nodes can be replaced by corresponding components, they have to be added to the pipeline with `add_component` and explicitly connected with the appropriate calls to `connect`. Here is an example: 49 50 **Haystack 1.x** 51 52 ```python 53 pipeline = Pipeline() 54 55 node_1 = SomeNode() 56 node_2 = AnotherNode() 57 58 pipeline.add_node(node_1, name="Node_1", inputs=["Query"]) 59 pipeline.add_node(node_2, name="Node_2", inputs=["Node_1"]) 60 ``` 61 62 **Haystack 2.x** 63 64 ```python 65 pipeline = Pipeline() 66 67 component_1 = SomeComponent() 68 component_2 = AnotherComponent() 69 70 pipeline.add_component("Comp_1", component_1) 71 pipeline.add_component("Comp_2", component_2) 72 73 pipeline.connect("Comp_1", "Comp_2") 74 ``` 75 76 In case a specific replacement component is not available for one of your nodes, migrating the pipeline might still be possible by: 77 78 - Either [creating a custom component](../concepts/components/custom-components.mdx), or 79 - Changing the pipeline logic, as the last resort. 80 81 :::info 82 Check out the [Pipelines](../concepts/pipelines.mdx) section of our 2.x documentation to understand how new pipelines work more granularly. 83 ::: 84 85 ### Document Stores 86 87 The fundamental concept of Document Stores as gateways to access text and metadata stored in a database didn’t change in Haystack 2.x, but there are significant differences against Haystack 1.x. 88 89 In Haystack 1.x, Document Stores were a special type of node that you can use in two ways: 90 91 - As the last node in an indexing pipeline (such as a pipeline whose ultimate goal is storing data in a database). 92 - As a normal Python instance passed to a Retriever node. 93 94 In Haystack 2.x, the Document Store is not a component, so to migrate the two use cases above to version 2.x, you can respectively: 95 96 - Replace the Document Store at the end of the pipeline with a [`DocumentWriter`](../pipeline-components/writers/documentwriter.mdx) component. 97 - Identify the right Retriever component and create it passing the Document Store instance, same as it is in Haystack 1.x. 98 99 ### Retrievers 100 101 Haystack 1.x provided a set of nodes that filter relevant documents from different data sources according to a given query. Each of those nodes implements a certain retrieval algorithm and supports one or more types of Document Stores. For example, the `BM25Retriever` node in Haystack 1.x can work seamlessly with OpenSearch and Elasticsearch but not with Qdrant; the `EmbeddingRetriever`, on the contrary, can work with all the three databases. 102 103 In Haystack 2.x, the concept is flipped, and each Document Store provides one or more retriever components, depending on which retrieval methods the underlying vector database supports. For example, the `OpenSearchDocumentStore` comes with [two Retriever components](../document-stores/opensearch-document-store.mdx#supported-retrievers), one relying on BM25, and the other on vector similarity. 104 105 To migrate a 1.x retrieval pipeline to 2.x, the first step is to identify the Document Store being used and replace the Retriever node with the corresponding Retriever component from Haystack 2.x with the Document Store of choice. For example, a `BM25Retriever` node using Elasticsearch in a Haystack 1.x pipeline should be replaced with the [`ElasticsearchBM25Retriever`](../pipeline-components/retrievers/elasticsearchbm25retriever.mdx) component. 106 107 ### PromptNode 108 109 The `PromptNode` in Haystack 1.x represented the gateway to any Large Language Model (LLM) inference provider, whether it is locally available or remote. Based on the name of the model, Haystack infers the right provider to call and forward the query. 110 111 In Haystack 2.x, the task of using LLMs is assigned to [Generators](../pipeline-components/generators.mdx). These are a set of components that are highly specialized and tailored for each inference provider. 112 113 The first step when migrating a pipeline with a `PromptNode` is to identify the model provider used and to replace the node with two components: 114 115 - A Generator component for the model provider of choice, 116 - A `PromptBuilder` or `ChatPromptBuilder` component to build the prompt to be used. 117 118 The [_Migration examples_](#migration-examples) section below shows how to port a `PromptNode` using OpenAI with a prompt template to a corresponding Haystack 2.x pipeline using the `OpenAIGenerator` in conjunction with a `PromptBuilder` component. 119 120 ### Agents 121 122 The agentic approach facilitates the answering of questions that are significantly more complex than those typically addressed by extractive or generative question answering techniques. 123 124 Haystack 1.x provided Agents, enabling the use of LLMs in a loop. 125 126 Currently in Haystack 2.x, you can build Agents using three main elements in a pipeline: Chat Generators, ToolInvoker component, and Tools. A standalone Agent abstraction in Haystack 2.x is in an experimental phase. 127 128 :::note[Agents Documentation Page] 129 130 Take a look at our 2.x [Agents](../concepts/agents.mdx) documentation page for more information and detailed examples. 131 ::: 132 133 ### REST API 134 135 Haystack 1.x enabled the deployment of pipelines through a RESTful API over HTTP. This feature is facilitated by a separate application named `rest_api` which is exclusively accessible in the form of a [source code on GitHub](https://github.com/deepset-ai/haystack/tree/v1.x/rest_api). 136 137 Haystack 2.x takes the same RESTful approach, but in this case, the application to be used to deploy pipelines is called [Hayhooks](../development/hayhooks.mdx) and can be installed with `pip install hayhooks`. 138 139 At the moment, porting an existing Haystack 1.x deployment using the `rest_api` project to Hayhooks would require a complete rewrite of the application. 140 141 ## Dependencies 142 143 In order to minimize runtime errors, Haystack 1.x was distributed in a package that’s quite large, as it tries to set up the Python environment with as many dependencies as possible. 144 145 In contrast, Haystack 2.x strives for a more streamlined approach, offering a minimal set of dependencies right out of the box. It features a system that issues a warning when an additional dependency is required, thereby providing the user with the necessary instructions. 146 147 To make sure all the dependencies are satisfied when migrating a Haystack 1.x application to version 2.x, a good strategy is to run end-to-end tests and cover all the execution paths to ensure all the required dependencies are available in the target Python environment. 148 149 ## Migrating Components 150 151 This table outlines which component (or a group of components) can be used to replace a certain node when porting a Haystack 1.x pipeline to the latest 2.x version. It’s important to note that when a Haystack 2.x replacement is not available, this doesn’t necessarily mean we are planning this feature. 152 153 If you need help migrating a 1.x node without a 2.x counterpart, open an [issue](https://github.com/deepset-ai/haystack/issues) in Haystack GitHub repository. 154 155 ### Data Handling 156 157 | Haystack 1.x | Description | Haystack 2.x | 158 | --- | --- | --- | 159 | Crawler | Scrapes text from websites. **Example usage:** To run searches on your website content. | Not Available | 160 | DocumentClassifier | Classifies documents by attaching metadata to them. **Example usage:** Labeling documents by their characteristic (for example, sentiment). | [TransformersZeroShotDocumentClassifier](../pipeline-components/classifiers/transformerszeroshotdocumentclassifier.mdx) | 161 | DocumentLanguageClassifier | Detects the language of the documents you pass to it and adds it to the document metadata. | [DocumentLanguageClassifier](../pipeline-components/classifiers/documentlanguageclassifier.mdx) | 162 | EntityExtractor | Extracts predefined entities out of a piece of text. **Example usage:** Named entity extraction (NER). | [NamedEntityExtractor](../pipeline-components/extractors/namedentityextractor.mdx) | 163 | FileClassifier | Distinguishes between text, PDF, Markdown, Docx, and HTML files. **Example usage:** Routing files to appropriate converters (for example, it routes PDF files to `PDFToTextConverter`). | [FileTypeRouter](../pipeline-components/routers/filetyperouter.mdx) | 164 | FileConverter | Cleans and splits documents in different formats. **Example usage:** In indexing pipelines, extracting text from a file and casting it into the Document class format. | [Converters](../pipeline-components/converters.mdx) | 165 | PreProcessor | Cleans and splits documents. **Example usage:** Normalizing white spaces, getting rid of headers and footers, splitting documents into smaller ones. | [PreProcessors](../pipeline-components/preprocessors.mdx) | 166 167 ### Semantic Search 168 169 | Haystack 1.x | Description | Haystack 2.x | 170 | --- | --- | --- | 171 | Ranker | Orders documents based on how relevant they are to the query. **Example usage:** In a query pipeline, after a keyword-based Retriever to rank the documents it returns. | [Rankers](../pipeline-components/rankers.mdx) | 172 | Reader | Finds an answer by selecting a text span in documents. **Example usage:** In a query pipeline when you want to know the location of the answer. | [ExtractiveReader](../pipeline-components/readers/extractivereader.mdx) | 173 | Retriever | Fetches relevant documents from the Document Store. **Example usage:** Coupling Retriever with a Reader in a query pipeline to speed up the search (the Reader only goes through the documents it gets from the Retriever). | [Retrievers](../pipeline-components/retrievers.mdx) | 174 | QuestionGenerator | When given a document, it generates questions this document can answer. **Example usage:** Auto-suggested questions in your search app. | Prompt [Builders](../pipeline-components/builders.mdx) with dedicated prompt, [Generators](../pipeline-components/generators.mdx) | 175 176 ### Prompts and LLMs 177 178 | Haystack 1.x | Description | Haystack 2.x | 179 | --- | --- | --- | 180 | PromptNode | Uses large language models to perform various NLP tasks in a pipeline or on its own. **Example usage:** It's a very versatile component that can perform tasks like summarization, question answering, translation, and more. | Prompt [Builders](../pipeline-components/builders.mdx),[Generators](../pipeline-components/generators.mdx) | 181 182 ### Routing 183 184 | Haystack 1.x | Description | Haystack 2.x | 185 | --- | --- | --- | 186 | QueryClassifier | Categorizes queries. **Example usage:** Distinguishing between keyword queries and natural language questions and routing them to the Retrievers that can handle them best. | [TransformersZeroShotTextRouter](../pipeline-components/routers/transformerszeroshottextrouter.mdx) <br />[TransformersTextRouter](../pipeline-components/routers/transformerstextrouter.mdx) | 187 | RouteDocuments | Routes documents to different branches of your pipeline based on their content type or metadata field. **Example usage:** Routing table data to `TableReader` and text data to `TransfomersReader` for better handling. | [Routers](../pipeline-components/routers.mdx) | 188 189 ### Utility Components 190 191 | Haystack 1.x | Description | Haystack 2.x | 192 | --- | --- | --- | 193 | DocumentMerger | Concatenates multiple documents into a single one. **Example usage: **Merge the documents to summarize in a summarization pipeline. | Prompt [Builders](../pipeline-components/builders.mdx) | 194 | Docs2Answers | Converts Documents into Answers. **Example usage:** When using REST API for document retrieval. REST API expects Answer as output, you can use `Doc2Answer` as the last node to convert the retrieved documents to answers. | [AnswerBuilder](../pipeline-components/builders/answerbuilder.mdx) | 195 | JoinAnswers | Takes answers returned by multiple components and joins them in a single list of answers. **Example usage:** For running queries on different document types (for example, tables and text), where the documents are routed to different readers, and each reader returns a separate list of answers. | [AnswerJoiner](../pipeline-components/joiners/answerjoiner.mdx) | 196 | JoinDocuments | Takes documents returned by different components and joins them to form one list of documents. **Example usage:** In document retrieval pipelines, where there are different types of documents, each routed to a different Retriever. Each Retriever returns a separate list of documents, and you can join them into one list using `JoinDocuments`. | [DocumentJoiner](../pipeline-components/joiners/documentjoiner.mdx) | 197 | Shaper | Currently functions mostly as `PromptNode` helper making sure the `PromptNode` input or output is correct. **Example usage:** In a question answering pipeline using `PromptNode`, where the `PromptTemplate` expects questions as input, while Haystack pipelines use query. You can use Shaper to rename queries to questions. | Prompt [Builders](../pipeline-components/builders.mdx) | 198 | Summarizer | Creates an overview of a document. **Example usage:** To get a glimpse of the documents the Retriever is returning. | Prompt [Builders](../pipeline-components/builders.mdx) with dedicated prompt, [Generators](../pipeline-components/generators.mdx) | 199 | TransformersImageToText | Generates captions for images. **Example usage:** Automatically generate captions for a list of images that you can later use in your knowledge base. | [VertexAIImageQA](../pipeline-components/generators/vertexaiimageqa.mdx) | 200 | Translator | Translates text from one language into another. **Example usage:** Running searches on documents in other languages. | Prompt [Builders](../pipeline-components/builders.mdx) with dedicated prompt, [Generators](../pipeline-components/generators.mdx) | 201 202 ### Extras 203 204 | Haystack 1.x | Description | Haystack 2.x | 205 | --- | --- | --- | 206 | AnswerToSpeech | Converts text answers into speech answers. **Example usage:** Improving accessibility of your search system by providing a way to have the answer and its context read out loud. | [ElevenLabs](https://haystack.deepset.ai/integrations/elevenlabs) Integration | 207 | DocumentToSpeech | Converts text documents to speech documents. **Example usage:** Improving accessibility of a document retrieval pipeline by providing the option to read documents out loud. | [ElevenLabs](https://haystack.deepset.ai/integrations/elevenlabs) Integration | 208 209 ## Migration examples 210 211 :::info 212 This section might grow as we assist users with their use cases. 213 ::: 214 215 ### Indexing Pipeline 216 217 <details> 218 219 <summary>Haystack 1.x</summary> 220 221 ```python 222 from haystack.document_stores import InMemoryDocumentStore 223 from haystack.nodes.file_classifier import FileTypeClassifier 224 from haystack.nodes.file_converter import TextConverter 225 from haystack.nodes.preprocessor import PreProcessor 226 from haystack.pipelines import Pipeline 227 228 ## Initialize a DocumentStore 229 document_store = InMemoryDocumentStore() 230 231 ## Indexing Pipeline 232 indexing_pipeline = Pipeline() 233 234 ## Makes sure the file is a TXT file (FileTypeClassifier node) 235 classifier = FileTypeClassifier() 236 indexing_pipeline.add_node(classifier, name="Classifier", inputs=["File"]) 237 238 ## Converts a file into text and performs basic cleaning (TextConverter node) 239 text_converter = TextConverter(remove_numeric_tables=True) 240 indexing_pipeline.add_node( 241 text_converter, 242 name="Text_converter", 243 inputs=["Classifier.output_1"], 244 ) 245 246 ## Pre-processes the text by performing splits and adding metadata to the text (Preprocessor node) 247 preprocessor = PreProcessor( 248 clean_whitespace=True, 249 clean_empty_lines=True, 250 split_length=100, 251 split_overlap=50, 252 split_respect_sentence_boundary=True, 253 ) 254 indexing_pipeline.add_node(preprocessor, name="Preprocessor", inputs=["Text_converter"]) 255 256 ## - Writes the resulting documents into the document store 257 indexing_pipeline.add_node( 258 document_store, 259 name="Document_Store", 260 inputs=["Preprocessor"], 261 ) 262 263 ## Then we run it with the documents and their metadata as input 264 result = indexing_pipeline.run(file_paths=file_paths, meta=files_metadata) 265 ``` 266 267 </details> 268 269 <details> 270 271 <summary>Haystack 2.x</summary> 272 273 ```python 274 from haystack import Pipeline 275 from haystack.components.routers import FileTypeRouter 276 from haystack.document_stores.in_memory import InMemoryDocumentStore 277 from haystack.components.converters import TextFileToDocument 278 from haystack.components.preprocessors import DocumentCleaner, DocumentSplitter 279 from haystack.components.writers import DocumentWriter 280 281 ## Initialize a DocumentStore 282 document_store = InMemoryDocumentStore() 283 284 ## Indexing Pipeline 285 indexing_pipeline = Pipeline() 286 287 ## Makes sure the file is a TXT file (FileTypeRouter component) 288 classifier = FileTypeRouter(mime_types=["text/plain"]) 289 indexing_pipeline.add_component("file_type_router", classifier) 290 291 ## Converts a file into a Document (TextFileToDocument component) 292 text_converter = TextFileToDocument() 293 indexing_pipeline.add_component("text_converter", text_converter) 294 295 ## Performs basic cleaning (DocumentCleaner component) 296 cleaner = DocumentCleaner( 297 remove_empty_lines=True, 298 remove_extra_whitespaces=True, 299 ) 300 indexing_pipeline.add_component("cleaner", cleaner) 301 302 ## Pre-processes the text by performing splits and adding metadata to the text (DocumentSplitter component) 303 preprocessor = DocumentSplitter(split_by="passage", split_length=100, split_overlap=50) 304 indexing_pipeline.add_component("preprocessor", preprocessor) 305 306 ## - Writes the resulting documents into the document store 307 indexing_pipeline.add_component("writer", DocumentWriter(document_store)) 308 309 ## Connect all the components 310 indexing_pipeline.connect("file_type_router.text/plain", "text_converter") 311 indexing_pipeline.connect("text_converter", "cleaner") 312 indexing_pipeline.connect("cleaner", "preprocessor") 313 indexing_pipeline.connect("preprocessor", "writer") 314 315 ## Then we run it with the documents and their metadata as input 316 result = indexing_pipeline.run({"file_type_router": {"sources": file_paths}}) 317 ``` 318 319 </details> 320 321 ### Query Pipeline 322 323 <details> 324 325 <summary>Haystack 1.x</summary> 326 327 ```python 328 from haystack.document_stores import InMemoryDocumentStore 329 from haystack.pipelines import ExtractiveQAPipeline 330 from haystack import Document 331 from haystack.nodes import BM25Retriever 332 from haystack.nodes import FARMReader 333 334 document_store = InMemoryDocumentStore(use_bm25=True) 335 document_store.write_documents( 336 [ 337 Document(content="Paris is the capital of France."), 338 Document(content="Berlin is the capital of Germany."), 339 Document(content="Rome is the capital of Italy."), 340 Document(content="Madrid is the capital of Spain."), 341 ], 342 ) 343 344 retriever = BM25Retriever(document_store=document_store) 345 reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2") 346 extractive_qa_pipeline = ExtractiveQAPipeline(reader, retriever) 347 348 query = "What is the capital of France?" 349 result = extractive_qa_pipeline.run( 350 query=query, 351 params={"Retriever": {"top_k": 10}, "Reader": {"top_k": 5}}, 352 ) 353 ``` 354 355 </details> 356 357 <details> 358 359 <summary>Haystack 2.x</summary> 360 361 ```python 362 from haystack.document_stores.in_memory import InMemoryDocumentStore 363 from haystack import Document, Pipeline 364 from haystack.components.retrievers.in_memory import InMemoryBM25Retriever 365 from haystack.components.readers import ExtractiveReader 366 367 document_store = InMemoryDocumentStore() 368 document_store.write_documents( 369 [ 370 Document(content="Paris is the capital of France."), 371 Document(content="Berlin is the capital of Germany."), 372 Document(content="Rome is the capital of Italy."), 373 Document(content="Madrid is the capital of Spain."), 374 ], 375 ) 376 377 retriever = InMemoryBM25Retriever(document_store) 378 reader = ExtractiveReader(model="deepset/roberta-base-squad2") 379 extractive_qa_pipeline = Pipeline() 380 extractive_qa_pipeline.add_component("retriever", retriever) 381 extractive_qa_pipeline.add_component("reader", reader) 382 extractive_qa_pipeline.connect("retriever", "reader") 383 384 query = "What is the capital of France?" 385 result = extractive_qa_pipeline.run( 386 data={ 387 "retriever": {"query": query, "top_k": 3}, 388 "reader": {"query": query, "top_k": 2}, 389 }, 390 ) 391 ``` 392 393 </details> 394 395 ### RAG Pipeline 396 397 <details> 398 399 <summary>Haystack 1.x</summary> 400 401 ```python 402 from datasets import load_dataset 403 404 from haystack.pipelines import Pipeline 405 from haystack.document_stores import InMemoryDocumentStore 406 from haystack.nodes import EmbeddingRetriever, PromptNode, PromptTemplate, AnswerParser 407 408 document_store = InMemoryDocumentStore(embedding_dim=384) 409 dataset = load_dataset("bilgeyucel/seven-wonders", split="train") 410 document_store.write_documents(dataset) 411 retriever = EmbeddingRetriever( 412 embedding_model="sentence-transformers/all-MiniLM-L6-v2", 413 document_store=document_store, 414 top_k=2, 415 ) 416 document_store.update_embeddings(retriever) 417 418 rag_prompt = PromptTemplate( 419 prompt="""Synthesize a comprehensive answer from the following text for the given question. 420 Provide a clear and concise response that summarizes the key points and information presented in the text. 421 Your answer should be in your own words and be no longer than 50 words. 422 \n\n Related text: {join(documents)} \n\n Question: {query} \n\n Answer:""", 423 output_parser=AnswerParser(), 424 ) 425 426 prompt_node = PromptNode( 427 model_name_or_path="gpt-3.5-turbo", 428 api_key=OPENAI_API_KEY, 429 default_prompt_template=rag_prompt, 430 ) 431 432 pipe = Pipeline() 433 pipe.add_node(component=retriever, name="retriever", inputs=["Query"]) 434 pipe.add_node(component=prompt_node, name="prompt_node", inputs=["retriever"]) 435 436 output = pipe.run(query="What does Rhodes Statue look like?") 437 ``` 438 439 </details> 440 441 <details> 442 443 <summary>Haystack 2.x</summary> 444 445 ```python 446 from datasets import load_dataset 447 448 from haystack import Document, Pipeline 449 from haystack.document_stores.in_memory import InMemoryDocumentStore 450 from haystack.components.builders import PromptBuilder 451 from haystack.components.generators import OpenAIGenerator 452 from haystack.components.embedders import SentenceTransformersDocumentEmbedder 453 from haystack.components.embedders import SentenceTransformersTextEmbedder 454 from haystack.components.retrievers import InMemoryEmbeddingRetriever 455 456 document_store = InMemoryDocumentStore() 457 dataset = load_dataset("bilgeyucel/seven-wonders", split="train") 458 embedder = SentenceTransformersDocumentEmbedder( 459 "sentence-transformers/all-MiniLM-L6-v2", 460 ) 461 embedder.warm_up() 462 output = embedder.run([Document(**ds) for ds in dataset]) 463 document_store.write_documents(output.get("documents")) 464 465 template = """ 466 Given the following information, answer the question. 467 468 Context: 469 {% for document in documents %} 470 {{ document.content }} 471 {% endfor %} 472 473 Question: {{question}} 474 Answer: 475 """ 476 prompt_builder = PromptBuilder(template=template) 477 478 retriever = InMemoryEmbeddingRetriever(document_store=document_store, top_k=2) 479 generator = OpenAIGenerator(model="gpt-3.5-turbo") 480 query_embedder = SentenceTransformersTextEmbedder( 481 model="sentence-transformers/all-MiniLM-L6-v2", 482 ) 483 484 basic_rag_pipeline = Pipeline() 485 basic_rag_pipeline.add_component("text_embedder", query_embedder) 486 basic_rag_pipeline.add_component("retriever", retriever) 487 basic_rag_pipeline.add_component("prompt_builder", prompt_builder) 488 basic_rag_pipeline.add_component("llm", generator) 489 490 basic_rag_pipeline.connect("text_embedder.embedding", "retriever.query_embedding") 491 basic_rag_pipeline.connect("retriever", "prompt_builder.documents") 492 basic_rag_pipeline.connect("prompt_builder", "llm") 493 494 query = "What does Rhodes Statue look like?" 495 output = basic_rag_pipeline.run( 496 {"text_embedder": {"text": query}, "prompt_builder": {"question": query}}, 497 ) 498 ``` 499 500 </details> 501 502 ## Documentation and Tutorials for Haystack 1.x 503 504 You can access old tutorials in the [GitHub history](https://github.com/deepset-ai/haystack-tutorials/tree/5917718cbfbb61410aab4121ee6fe754040a5dc7) and download the Haystack 1.x documentation as a [ZIP file](https://core-engineering.s3.eu-central-1.amazonaws.com/public/docs/haystack-v1-docs.zip). 505 506 The ZIP file contains documentation for all minor releases from version 1.0 to 1.26. 507 508 To download documentation for a specific release, replace the version number in the following URL: `https://core-engineering.s3.eu-central-1.amazonaws.com/public/docs/v1.26.zip`.