1  ---
 2  title: "AnthropicGenerator"
 3  id: anthropicgenerator
 4  slug: "/anthropicgenerator"
 5  description: "This component enables text completions using Anthropic large language models (LLMs)."
 6  ---
 7  
 8  # AnthropicGenerator
 9  
10  This component enables text completions using Anthropic large language models (LLMs).
11  
12  |  |  |
13  | --- | --- |
14  | **Most common position in a pipeline** | After a [PromptBuilder](../builders/promptbuilder.mdx)  |
15  | **Mandatory init variables** | "api_key": An Anthropic API key. Can be set with `ANTHROPIC_API_KEY` env var. |
16  | **Mandatory run variables** | “prompt”: A string containing the prompt for the LLM |
17  | **Output variables** | “replies”: A list of strings with all the replies generated by the LLM  <br /> <br />”meta”: A list of dictionaries with the metadata associated with each reply, such as token count, finish reason, and so on |
18  | **API reference** | [Anthropic](/reference/integrations-anthropic) |
19  | **GitHub link** | https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/anthropic |
20  
21  ## Overview
22  
23  This integration supports Anthropic models such as `claude-3-5-sonnet-20240620`,`claude-3-opus-20240229`, `claude-3-haiku-20240307`, and similar. Although these LLMs are called chat models, the main prompt interface works with the string prompts. Check out the most recent full list in the [Anthropic documentation](https://docs.anthropic.com/en/docs/about-claude/models).
24  
25  ### Parameters
26  
27  `AnthropicGenerator` needs an Anthropic API key to work. You can provide this key in:
28  
29  - The `ANTHROPIC_API_KEY` environment variable (recommended)
30  - The `api_key` init parameter and Haystack [Secret](../../concepts/secret-management.mdx) API: `Secret.from_token("your-api-key-here")`
31  
32  Set your preferred Anthropic model in the `model` parameter when initializing the component.
33  
34  `AnthropicGenerator` requires a prompt to generate text, but you can pass any text generation parameters available in the Anthropic [Messaging API](https://docs.anthropic.com/en/api/messages) method directly to this component using the `generation_kwargs` parameter, both at initialization and to `run()` method. For more details on the parameters supported by the Anthropic API, see [Anthropic documentation](https://docs.anthropic.com).
35  
36  Finally, the component run method requires a single string prompt to generate text.
37  
38  ### Streaming
39  
40  This Generator supports [streaming](guides-to-generators/choosing-the-right-generator.mdx#streaming-support) the tokens from the LLM directly in output. To do so, pass a function to the `streaming_callback` init parameter.
41  
42  ## Usage
43  
44  Install the `anthropic-haystack` package to use the `AnthropicGenerator`:
45  
46  ```shell
47  pip install anthropic-haystack
48  ```
49  
50  ### On its own
51  
52  ```python
53  from haystack_integrations.components.generators.anthropic import AnthropicGenerator
54  
55  generator = AnthropicGenerator()
56  print(generator.run("What's Natural Language Processing? Be brief."))
57  ```
58  
59  ### In a pipeline
60  
61  You can also use `AnthropicGenerator` with the Anthropic models in your pipeline.
62  
63  ```python
64  from haystack import Pipeline
65  from haystack.components.builders import PromptBuilder
66  from haystack_integrations.components.generators.anthropic import AnthropicGenerator
67  from haystack.utils import Secret
68  
69  template = """
70  You are an assistant giving out valuable information to language learners.
71  Answer this question, be brief.
72  
73  Question: {{ query }}?
74  """
75  
76  pipe = Pipeline()
77  pipe.add_component("prompt_builder", PromptBuilder(template))
78  pipe.add_component("llm", AnthropicGenerator(Secret.from_env_var("ANTHROPIC_API_KEY")))
79  pipe.connect("prompt_builder", "llm")
80  
81  query = "What language is spoke in Germany?"
82  res = pipe.run(data={"prompt_builder": {"query": {query}}})
83  print(res)
84  ```