Sync Haystack API reference on Docusaurus (#9891)

Co-authored-by: anakin87 <[email protected]>

Author: HaystackBot

docs-website/reference/haystack-api/agents_api.md

@@ -1,7 +1,8 @@
 ---
-title: Agents
+title: "Agents"
 id: agents-api
-description: Tool-using agents with provider-agnostic chat model support.
+description: "Tool-using agents with provider-agnostic chat model support."
+slug: "/agents-api"
 ---
 
 <a id="agent"></a>
@@ -366,3 +367,4 @@ def from_dict(cls, data: dict[str, Any])
 ```
 
 Convert a dictionary back to a State object.
+

docs-website/reference/haystack-api/audio_api.md

@@ -1,7 +1,8 @@
 ---
-title: Audio
+title: "Audio"
 id: audio-api
-description: Transcribes audio files.
+description: "Transcribes audio files."
+slug: "/audio-api"
 ---
 
 <a id="whisper_local"></a>
@@ -263,3 +264,4 @@ Transcribes the list of audio files into a list of documents.
 A dictionary with the following keys:
 - `documents`: A list of documents, one document for each file.
 The content of each document is the transcribed text.
+

docs-website/reference/haystack-api/builders_api.md

@@ -1,7 +1,8 @@
 ---
-title: Builders
+title: "Builders"
 id: builders-api
-description: Extract the output of a Generator to an Answer format, and build prompts.
+description: "Extract the output of a Generator to an Answer format, and build prompts."
+slug: "/builders-api"
 ---
 
 <a id="answer_builder"></a>
@@ -507,3 +508,4 @@ Deserialize this component from a dictionary.
 **Returns**:
 
 The deserialized component.
+

docs-website/reference/haystack-api/cachings_api.md

@@ -1,7 +1,8 @@
 ---
-title: Caching
+title: "Caching"
 id: caching-api
-description: Checks if any document coming from the given URL is already present in the store.
+description: "Checks if any document coming from the given URL is already present in the store."
+slug: "/caching-api"
 ---
 
 <a id="cache_checker"></a>
@@ -106,3 +107,4 @@ Checks if any document associated with the specified cache field is already pres
 A dictionary with two keys:
 - `hits` - Documents that matched with at least one of the items.
 - `misses` - Items that were not present in any documents.
+

docs-website/reference/haystack-api/classifiers_api.md

@@ -1,7 +1,8 @@
 ---
-title: Classifiers
+title: "Classifiers"
 id: classifiers-api
-description: Classify documents based on the provided labels.
+description: "Classify documents based on the provided labels."
+slug: "/classifiers-api"
 ---
 
 <a id="document_language_classifier"></a>
@@ -258,3 +259,4 @@ the `details` key within the `classification` dictionary.
 
 A dictionary with the following key:
 - `documents`: A list of documents with an added metadata field called `classification`.
+

docs-website/reference/haystack-api/connectors_api.md

@@ -1,7 +1,8 @@
 ---
-title: Connectors
+title: "Connectors"
 id: connectors-api
-description: Various connectors to integrate with external services.
+description: "Various connectors to integrate with external services."
+slug: "/connectors-api"
 ---
 
 <a id="openapi_service"></a>
@@ -243,3 +244,4 @@ Invokes a REST endpoint specified in the OpenAPI specification.
 **Returns**:
 
 Dictionary containing the service response
+

docs-website/reference/haystack-api/converters_api.md

@@ -1,7 +1,8 @@
 ---
-title: Converters
+title: "Converters"
 id: converters-api
-description: Various converters to transform data from one format to another.
+description: "Various converters to transform data from one format to another."
+slug: "/converters-api"
 ---
 
 <a id="azure"></a>
@@ -144,30 +145,32 @@ The deserialized component.
 
 Converts CSV files to Documents.
 
-    By default, it uses UTF-8 encoding when converting files but
-    you can also set a custom encoding.
-    It can attach metadata to the resulting documents.
+By default, it uses UTF-8 encoding when converting files but
+you can also set a custom encoding.
+It can attach metadata to the resulting documents.
 
-    ### Usage example
+### Usage example
 
-    ```python
-    from haystack.components.converters.csv import CSVToDocument
-    converter = CSVToDocument()
-    results = converter.run(sources=["sample.csv"], meta={"date_added": datetime.now().isoformat()})
-    documents = results["documents"]
-    print(documents[0].content)
-    # 'col1,col2
-ow1,row1
-row2row2
-'
-    ```
+```python
+from haystack.components.converters.csv import CSVToDocument
+converter = CSVToDocument()
+results = converter.run(sources=["sample.csv"], meta={"date_added": datetime.now().isoformat()})
+documents = results["documents"]
+print(documents[0].content)
+# 'col1,col2\nrow1,row1\nrow2,row2\n'
+```
 
 <a id="csv.CSVToDocument.__init__"></a>
 
 #### CSVToDocument.\_\_init\_\_
 
 ```python
-def __init__(encoding: str = "utf-8", store_full_path: bool = False)
+def __init__(encoding: str = "utf-8",
+             store_full_path: bool = False,
+             *,
+             conversion_mode: Literal["file", "row"] = "file",
+             delimiter: str = ",",
+             quotechar: str = '"')
 ```
 
 Creates a CSVToDocument component.
@@ -179,6 +182,10 @@ If the encoding is specified in the metadata of a source ByteStream,
 it overrides this value.
 - `store_full_path`: If True, the full path of the file is stored in the metadata of the document.
 If False, only the file name is stored.
+- `conversion_mode`: - "file" (default): one Document per CSV file whose content is the raw CSV text.
+- "row": convert each CSV row to its own Document (requires `content_column` in `run()`).
+- `delimiter`: CSV delimiter used when parsing in row mode (passed to ``csv.DictReader``).
+- `quotechar`: CSV quote character used when parsing in row mode (passed to ``csv.DictReader``).
 
 <a id="csv.CSVToDocument.run"></a>
 
@@ -187,14 +194,19 @@ If False, only the file name is stored.
 ```python
 @component.output_types(documents=list[Document])
 def run(sources: list[Union[str, Path, ByteStream]],
+        *,
+        content_column: Optional[str] = None,
         meta: Optional[Union[dict[str, Any], list[dict[str, Any]]]] = None)
 ```
 
-Converts a CSV file to a Document.
+Converts CSV files to a Document (file mode) or to one Document per row (row mode).
 
 **Arguments**:
 
 - `sources`: List of file paths or ByteStream objects.
+- `content_column`: **Required when** ``conversion_mode="row"``.
+The column name whose values become ``Document.content`` for each row.
+The column must exist in the CSV header.
 - `meta`: Optional metadata to attach to the documents.
 This value can be either a list of dictionaries or a single dictionary.
 If it's a single dictionary, its content is added to the metadata of all produced documents.
@@ -1618,3 +1630,4 @@ If `sources` contains ByteStream objects, their `meta` will be added to the outp
 
 A dictionary with the following keys:
 - `documents`: Created documents
+

docs-website/reference/haystack-api/data_classess_api.md

@@ -1,7 +1,8 @@
 ---
-title: Data Classes
+title: "Data Classes"
 id: data-classess-api
-description: Core classes that carry data through the system.
+description: "Core classes that carry data through the system."
+slug: "/data-classess-api"
 ---
 
 <a id="answer"></a>
@@ -1329,3 +1330,4 @@ The runtime callback takes precedence over the initial callback.
 **Returns**:
 
 The selected callback.
+

docs-website/reference/haystack-api/document_stores_api.md

@@ -1,7 +1,8 @@
 ---
-title: Document Stores
+title: "Document Stores"
 id: document-stores-api
-description: Stores your texts and meta data and provides them to the Retriever at query time.
+description: "Stores your texts and meta data and provides them to the Retriever at query time."
+slug: "/document-stores-api"
 ---
 
 <a id="document_store"></a>
@@ -378,3 +379,4 @@ Retrieves documents that are most similar to the query embedding using a vector
 **Returns**:
 
 A list of the top_k documents most relevant to the query.
+

docs-website/reference/haystack-api/document_writers_api.md

@@ -1,7 +1,8 @@
 ---
-title: Document Writers
+title: "Document Writers"
 id: document-writers-api
-description: Writes Documents to a DocumentStore.
+description: "Writes Documents to a DocumentStore."
+slug: "/document-writers-api"
 ---
 
 <a id="document_writer"></a>
@@ -136,3 +137,4 @@ but can be used with `await` in async code.
 **Returns**:
 
 Number of documents written to the document store.
+