apify-haystack 0.0.1a4__tar.gz → 0.0.1a6__tar.gz

{apify_haystack-0.0.1a4 → apify_haystack-0.0.1a6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: apify_haystack
-Version: 0.0.1a4
+Version: 0.0.1a6
 Summary: Apify-haystack integration
 Home-page: https://apify.com
 License: Apache-2.0
@@ -19,7 +19,7 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Software Development :: Libraries
 Requires-Dist: apify-client (>=1.7.1,<2.0.0)
-Requires-Dist: haystack-ai (>=2.3.0,<3.0.0)
+Requires-Dist: haystack-ai (>=2.3.1,<3.0.0)
 Requires-Dist: python-dotenv (>=1.0.1,<2.0.0)
 Project-URL: Changelog, https://github.com/apify/apify-haystack/blob/master/CHANGELOG.md
 Project-URL: Documentation, https://github.com/apify/apify-haystack
@@ -29,11 +29,12 @@ Description-Content-Type: text/markdown
 
 # Apify-Haystack integration
 
-Apify-Haystack integration allows to quickly fetch results from Apify Actors.
+The Apify-Haystack integration allows easy interaction between the Apify platform and Haystack.
 
-🚧 **Work In Progress** 🚧
+Apify is a platform for web scraping, data extraction, and web automation tasks.
+It provides serverless applications called Actors for different tasks, like crawling websites, and scraping Facebook, Instagram, and Google results, etc.
 
-This project is currently under active development.
+Haystack offers an ecosystem of tools for building, managing, and deploying search engines and LLM applications.
 
 ## Installation
 
@@ -45,9 +46,12 @@ pip install apify-haystack
 
 ## Examples
 
-Here are some practical examples to help you get started ...
+See the [examples directory](https://github.com/apify/apify-haystack/blob/master/src/apify_haystack/examples) for more examples, here is a list of few of them
 
-## Features
+- Load a dataset from Apify and convert it to Haystack Documents
+- Call Apify Actor and load a dataset to convert it to Haystack Documents
+- Crawl website, scrape text content, and store it in the InMemoryDocumentStore
+- Retrieval-Augmented Generation (RAG): Extracting text from a website & question answering
 
 ## Support
 
@@ -56,7 +60,7 @@ For questions, you can ask on [Stack Overflow](https://stackoverflow.com/questio
 
 ## Contributing
 
-Your code contributions are welcome, and you'll be praised for eternity!
+Your code contributions are welcome.
 If you have any ideas for improvements, either submit an issue or create a pull request.
 For contribution guidelines and the code of conduct, see [CONTRIBUTING.md](https://github.com/apify/apify-haystack/blob/master/CONTRIBUTING.md).
 

{apify_haystack-0.0.1a4 → apify_haystack-0.0.1a6}/README.md

@@ -1,10 +1,11 @@
 # Apify-Haystack integration
 
-Apify-Haystack integration allows to quickly fetch results from Apify Actors.
+The Apify-Haystack integration allows easy interaction between the Apify platform and Haystack.
 
-🚧 **Work In Progress** 🚧
+Apify is a platform for web scraping, data extraction, and web automation tasks.
+It provides serverless applications called Actors for different tasks, like crawling websites, and scraping Facebook, Instagram, and Google results, etc.
 
-This project is currently under active development.
+Haystack offers an ecosystem of tools for building, managing, and deploying search engines and LLM applications.
 
 ## Installation
 
@@ -16,9 +17,12 @@ pip install apify-haystack
 
 ## Examples
 
-Here are some practical examples to help you get started ...
+See the [examples directory](https://github.com/apify/apify-haystack/blob/master/src/apify_haystack/examples) for more examples, here is a list of few of them
 
-## Features
+- Load a dataset from Apify and convert it to Haystack Documents
+- Call Apify Actor and load a dataset to convert it to Haystack Documents
+- Crawl website, scrape text content, and store it in the InMemoryDocumentStore
+- Retrieval-Augmented Generation (RAG): Extracting text from a website & question answering
 
 ## Support
 
@@ -27,7 +31,7 @@ For questions, you can ask on [Stack Overflow](https://stackoverflow.com/questio
 
 ## Contributing
 
-Your code contributions are welcome, and you'll be praised for eternity!
+Your code contributions are welcome.
 If you have any ideas for improvements, either submit an issue or create a pull request.
 For contribution guidelines and the code of conduct, see [CONTRIBUTING.md](https://github.com/apify/apify-haystack/blob/master/CONTRIBUTING.md).
 

{apify_haystack-0.0.1a4 → apify_haystack-0.0.1a6}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "apify_haystack"
-version = "0.0.1a4"
+version = "0.0.1a6"
 description = "Apify-haystack integration"
 authors = ["Apify Technologies s.r.o. <support@apify.com>"]
 homepage = "https://apify.com"
@@ -44,7 +44,7 @@ keywords = [
 [tool.poetry.dependencies]
 python = "^3.9"
 apify-client = "^1.7.1"
-haystack-ai = "^2.3.0"
+haystack-ai = "^2.3.1"
 python-dotenv = "^1.0.1"
 
 [tool.poetry.group.dev.dependencies]

{apify_haystack-0.0.1a4 → apify_haystack-0.0.1a6}/src/apify_haystack/examples/crawl_and_process_data.py

@@ -1,4 +1,6 @@
 """
+Crawl website, scrape text content, and store it in the InMemoryDocumentStore.
+
 This script demonstrates how to extract content from a website using the Apify actor: Website Content Crawler.
 The content is then cleaned, split into smaller chunks, embedded, and stored in the InMemoryDocumentStore.
 
@@ -78,7 +80,7 @@ pipe.run({"document_loader": {}})
 
 print(f"Added {document_store.count_documents()} to vector from Website Content Crawler")
 
-print("\nRetrieving documents from the document store: query='Haystack'")
-print("query='Haystack'\n")
+print("Retrieving documents from the document store: query='Haystack'")
+print("query='Haystack'")
 for doc in document_store.bm25_retrieval("Haystack", top_k=1):
     print(doc)

{apify_haystack-0.0.1a4 → apify_haystack-0.0.1a6}/src/apify_haystack/examples/rag_with_crawled_website.py

@@ -1,8 +1,5 @@
 """
-Retrieval-Augmented Generation (RAG)
-
-This script demonstrates how to extract text content from a website, store it in a vector database, and use
-it for question answering.
+Retrieval-Augmented Generation (RAG): Extracting text content from a website and using it for question answering.
 
 Steps involved:
 - Load environment variables, including API keys.
@@ -35,9 +32,9 @@ from haystack.utils.auth import Secret
 from apify_haystack import ApifyDatasetFromActorCall
 
 # Set APIFY-API-TOKEN here or use it from .env file
+load_dotenv()
 apify_token = "" or os.getenv("APIFY_API_TOKEN")
 openai_api_key = "" or os.getenv("OPENAI_API_KEY")
-load_dotenv()
 
 actor_id = "apify/website-content-crawler"
 run_input = {
@@ -55,6 +52,7 @@ apify_dataset_loader = ApifyDatasetFromActorCall(
 )
 
 # Components
+print("Initializing components...")
 document_store = InMemoryDocumentStore()
 
 docs_embedder = OpenAIDocumentEmbedder(api_key=Secret.from_token(openai_api_key))
@@ -82,6 +80,7 @@ Answer:
 prompt_builder = PromptBuilder(template=template)
 
 # Add components to your pipeline
+print("Initializing pipeline...")
 pipe = Pipeline()
 pipe.add_component("embedder", text_embedder)
 pipe.add_component("retriever", retriever)
@@ -95,6 +94,9 @@ pipe.connect("prompt_builder", "llm")
 
 question = "What is haystack?"
 
+print("Running pipeline ... crawling will take some time ...")
+print("You can visit https://console.apify.com/actors/runs to monitor the progress")
+
 response = pipe.run({"embedder": {"text": question}, "prompt_builder": {"question": question}})
 
 print(f"question: {question}")
@@ -108,4 +110,5 @@ examples = [
 
 for example in examples:
     response = pipe.run({"embedder": {"text": example}, "prompt_builder": {"question": example}})
-    print(response["llm"]["replies"][0])
+    print(f"question: {question}")
+    print(f"answer: {response['llm']['replies'][0]}")