Merge branch 'main' into add-pgvector-datastore

integrations/ollama/example/example.py

@@ -0,0 +1,55 @@
+# In order to run this example, you will need to have an instance of Ollama running with the
+# orca-mini model downloaded. We suggest you use the following commands to serve an orca-mini
+# model from Ollama
+#
+# docker run -d -p 11434:11434 --name ollama ollama/ollama:latest
+# docker exec ollama ollama pull orca-mini
+
+from haystack import Document, Pipeline
+from haystack.components.builders.prompt_builder import PromptBuilder
+from haystack.components.retrievers import InMemoryBM25Retriever
+from haystack.document_stores.in_memory import InMemoryDocumentStore
+
+from ollama_haystack import OllamaGenerator
+
+document_store = InMemoryDocumentStore()
+document_store.write_documents(
+    [
+        Document(content="Super Mario was an important politician"),
+        Document(content="Mario owns several castles and uses them to conduct important political business"),
+        Document(
+            content="Super Mario was a successful military leader who fought off several invasion attempts by "
+            "his arch rival - Bowser"
+        ),
+    ]
+)
+
+query = "Who is Super Mario?"
+
+template = """
+Given only the following information, answer the question.
+Ignore your own knowledge.
+
+Context:
+{% for document in documents %}
+    {{ document.content }}
+{% endfor %}
+
+Question: {{ query }}?
+"""
+pipe = Pipeline()
+
+pipe.add_component("retriever", InMemoryBM25Retriever(document_store=document_store))
+pipe.add_component("prompt_builder", PromptBuilder(template=template))
+pipe.add_component("llm", OllamaGenerator(model="orca-mini"))
+pipe.connect("retriever", "prompt_builder.documents")
+pipe.connect("prompt_builder", "llm")
+
+response = pipe.run({"prompt_builder": {"query": query}, "retriever": {"query": query}})
+
+print(response["llm"]["replies"])
+# An expected response - the output is not deterministic:
+# ['Based on the information provided, Super Mario is a successful military leader who fought
+# off several invasion attempts by his arch rival - Bowser. He is also an important politician and owns several
+# castles where he conducts political business. ' 'Therefore, it can be inferred that Super Mario is a combination of
+# both a military leader and an important politician.']

integrations/ollama/pyproject.toml

@@ -145,6 +145,8 @@ ban-relative-imports = "all"
 [tool.ruff.per-file-ignores]
 # Tests can use magic values, assertions, and relative imports
 "tests/**/*" = ["PLR2004", "S101", "TID252"]
+# Examples can print their output
+"example/**" = ["T201"]
 
 
 [tool.coverage.run]

integrations/ollama/src/ollama_haystack/generator.py

@@ -28,12 +28,12 @@ def __init__(
         :param url: The URL of the generation endpoint of a running Ollama instance.
             Default is "http://localhost:11434/api/generate".
         :param generation_kwargs: Optional arguments to pass to the Ollama generation endpoint, such as temperature,
-            top_p, etc. See the
+            top_p, and others. See the available arguments in
             [Ollama docs](https://github.com/jmorganca/ollama/blob/main/docs/modelfile.md#valid-parameters-and-values).
         :param system_prompt: Optional system message (overrides what is defined in the Ollama Modelfile).
         :param template: The full prompt template (overrides what is defined in the Ollama Modelfile).
         :param raw: If True, no formatting will be applied to the prompt. You may choose to use the raw parameter
-            if you are specifying a full templated prompt in your request to the API.
+            if you are specifying a full templated prompt in your API request.
         :param timeout: The number of seconds before throwing a timeout error from the Ollama API.
             Default is 30 seconds.
         """
@@ -47,10 +47,12 @@ def __init__(
 
     def _create_json_payload(self, prompt: str, generation_kwargs=None) -> Dict[str, Any]:
         """
-        Returns A dictionary of JSON arguments for a POST request to an Ollama service
-        :param prompt: the prompt to generate a response for
-        :param generation_kwargs:
-        :return: A dictionary of arguments for a POST request to an Ollama service
+        Returns a dictionary of JSON arguments for a POST request to an Ollama service.
+        :param prompt: The prompt to generate a response for.
+        :param generation_kwargs: Optional arguments to pass to the Ollama generation endpoint, such as temperature,
+            top_p, and others. See the available arguments in
+            [Ollama docs](https://github.com/jmorganca/ollama/blob/main/docs/modelfile.md#valid-parameters-and-values).
+        :return: A dictionary of arguments for a POST request to an Ollama service.
         """
         generation_kwargs = generation_kwargs or {}
         return {
@@ -65,9 +67,9 @@ def _create_json_payload(self, prompt: str, generation_kwargs=None) -> Dict[str,
 
     def _convert_to_haystack_response(self, ollama_response: Response) -> Dict[str, List[Any]]:
         """
-        Convert a response from the Ollama API to the required Haystack format
-        :param ollama_response: A response (requests library) from the Ollama API
-        :return: A dictionary of the returned responses and metadata
+        Convert a response from the Ollama API to the required Haystack format.
+        :param ollama_response: A response (requests library) from the Ollama API.
+        :return: A dictionary of the returned responses and metadata.
         """
         resp_dict = ollama_response.json()
 
@@ -83,10 +85,10 @@ def run(
         generation_kwargs: Optional[Dict[str, Any]] = None,
     ):
         """
-        Run an Ollama Model on the a given prompt.
+        Run an Ollama Model on the given prompt.
         :param prompt: The prompt to generate a response for.
         :param generation_kwargs: Optional arguments to pass to the Ollama generation endpoint, such as temperature,
-            top_p, etc. See the
+            top_p, and others. See the available arguments in
             [Ollama docs](https://github.com/jmorganca/ollama/blob/main/docs/modelfile.md#valid-parameters-and-values).
         :return: A dictionary of the response and returned metadata
         """