diff --git a/.github/ISSUE_TEMPLATE/config.yml b/.github/ISSUE_TEMPLATE/config.yml index c2a8d86a0f..9d36944740 100644 --- a/.github/ISSUE_TEMPLATE/config.yml +++ b/.github/ISSUE_TEMPLATE/config.yml @@ -2,4 +2,4 @@ blank_issues_enabled: true contact_links: - name: Something unclear? Just ask :) url: https://github.com/deepset-ai/haystack/discussions/new - about: Start a Github discussion with your question \ No newline at end of file + about: Start a Github discussion with your question diff --git a/.github/labeler.yml b/.github/labeler.yml index adf6fab206..bc33834905 100644 --- a/.github/labeler.yml +++ b/.github/labeler.yml @@ -1,2 +1,2 @@ Proposal: -- proposals/text/* \ No newline at end of file +- proposals/text/* diff --git a/.github/workflows/labeler.yml b/.github/workflows/labeler.yml index 8348b9e6f7..d3e9adbd9e 100644 --- a/.github/workflows/labeler.yml +++ b/.github/workflows/labeler.yml @@ -12,4 +12,4 @@ jobs: steps: - uses: actions/labeler@v4 with: - repo-token: "${{ secrets.GITHUB_TOKEN }}" \ No newline at end of file + repo-token: "${{ secrets.GITHUB_TOKEN }}" diff --git a/annotation_tool/README.md b/annotation_tool/README.md index a17f965e89..cd4ee7a9ec 100644 --- a/annotation_tool/README.md +++ b/annotation_tool/README.md @@ -66,4 +66,4 @@ The manual (of a slightly earlier version) can be found [here](https://drive.goo - Please do not annotate this text - You can write down what is missing, or the cause why you cannot label the text + the text number and title. 8. Which browser to use? -- Please use the Chrome browser. The tool is not tested for other browsers. \ No newline at end of file +- Please use the Chrome browser. The tool is not tested for other browsers. diff --git a/code_of_conduct.txt b/code_of_conduct.txt index ec3b14cef1..c4814cb229 100644 --- a/code_of_conduct.txt +++ b/code_of_conduct.txt @@ -95,4 +95,4 @@ This Code of Conduct is adapted from the Contributor Covenant, version 2.0, avai Community Impact Guidelines were inspired by Mozilla’s code of conduct enforcement ladder. For answers to common questions about this code of conduct, see the FAQ at https://www.contributor-covenant.org/faq. -Translations are available at https://www.contributor-covenant.org/translations. \ No newline at end of file +Translations are available at https://www.contributor-covenant.org/translations. diff --git a/docker/README.md b/docker/README.md index 25537d1b16..fa447135f3 100644 --- a/docker/README.md +++ b/docker/README.md @@ -42,7 +42,7 @@ HAYSTACK_VERSION=mybranch_or_tag BASE_IMAGE_TAG_SUFFIX=latest docker buildx bake ### Multi-Platform Builds Haystack images support multiple architectures. But depending on your operating system and Docker -environment, you might not be able to build all of them locally. +environment, you might not be able to build all of them locally. You may encounter the following error when trying to build the image: @@ -68,4 +68,4 @@ other licenses (such as Bash, etc from the base distribution, along with any dir indirect dependencies of the primary software being contained). As for any pre-built image usage, it is the image user's responsibility to ensure that any -use of this image complies with any relevant licenses for all software contained within. \ No newline at end of file +use of this image complies with any relevant licenses for all software contained within. diff --git a/docs/_src/api/_static/floating_sidebar.css b/docs/_src/api/_static/floating_sidebar.css index e59adc6722..78d1423356 100644 --- a/docs/_src/api/_static/floating_sidebar.css +++ b/docs/_src/api/_static/floating_sidebar.css @@ -26,4 +26,4 @@ div.sphinxsidebar .logo img { div.sphinxsidebar .download a img { vertical-align: middle; -} \ No newline at end of file +} diff --git a/docs/_src/api/_templates/xxlayout.html b/docs/_src/api/_templates/xxlayout.html index de71588332..47ec94d1cf 100644 --- a/docs/_src/api/_templates/xxlayout.html +++ b/docs/_src/api/_templates/xxlayout.html @@ -43,4 +43,4 @@ }); {#- endif #} -{% endblock %} \ No newline at end of file +{% endblock %} diff --git a/docs/_src/api/api/crawler.md b/docs/_src/api/api/crawler.md index cdab2adef7..1c8fd6a9c0 100644 --- a/docs/_src/api/api/crawler.md +++ b/docs/_src/api/api/crawler.md @@ -182,4 +182,3 @@ E.g. 1) crawler_naming_function=lambda url, page_content: re.sub("[<>:'/\\|?*\0 **Returns**: Tuple({"paths": List of filepaths, ...}, Name of output edge) - diff --git a/docs/_src/api/api/document_classifier.md b/docs/_src/api/api/document_classifier.md index 18afebfd0a..ef76682d92 100644 --- a/docs/_src/api/api/document_classifier.md +++ b/docs/_src/api/api/document_classifier.md @@ -184,4 +184,3 @@ Documents are updated in place. **Returns**: List of Documents or list of lists of Documents enriched with meta information. - diff --git a/docs/_src/api/api/document_store.md b/docs/_src/api/api/document_store.md index e8a619075c..eae4ef2e92 100644 --- a/docs/_src/api/api/document_store.md +++ b/docs/_src/api/api/document_store.md @@ -5804,7 +5804,7 @@ namespace (vectors) if it exists, otherwise the document namespace (no-vectors). **Returns**: -`None`: +`None`: @@ -6056,4 +6056,3 @@ and UTC as default time zone. This method cannot be part of WeaviateDocumentStore, as this would result in a circular import between weaviate.py and filter_utils.py. - diff --git a/docs/_src/api/api/evaluation.md b/docs/_src/api/api/evaluation.md index 2a3f5054bd..33b8b0f9e4 100644 --- a/docs/_src/api/api/evaluation.md +++ b/docs/_src/api/api/evaluation.md @@ -163,4 +163,3 @@ https://huggingface.co/transformers/main_classes/model.html#transformers.PreTrai **Returns**: top_1_sas, top_k_sas, pred_label_matrix - diff --git a/docs/_src/api/api/extractor.md b/docs/_src/api/api/extractor.md index 200ee8a8de..5d59b914a4 100644 --- a/docs/_src/api/api/extractor.md +++ b/docs/_src/api/api/extractor.md @@ -194,4 +194,3 @@ This is a wrapper class to create a Pytorch dataset object from the data attribu - `model_inputs`: The data attribute of the output from a HuggingFace tokenizer which is needed to evaluate the forward pass of a token classification model. - diff --git a/docs/_src/api/api/file_classifier.md b/docs/_src/api/api/file_classifier.md index 767001b562..4d67d78578 100644 --- a/docs/_src/api/api/file_classifier.md +++ b/docs/_src/api/api/file_classifier.md @@ -42,4 +42,3 @@ Sends out files on a different output edge depending on their extension. **Arguments**: - `file_paths`: paths to route on different edges. - diff --git a/docs/_src/api/api/file_converter.md b/docs/_src/api/api/file_converter.md index e954390de1..532abb5e2d 100644 --- a/docs/_src/api/api/file_converter.md +++ b/docs/_src/api/api/file_converter.md @@ -734,4 +734,3 @@ in garbled text. attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. `"meta"` to this field (e.g. [`"content"`, `"meta"`]). In this case the id will be generated by using the content and the defined metadata. - diff --git a/docs/_src/api/api/generator.md b/docs/_src/api/api/generator.md index bda1b192bc..920cb628ef 100644 --- a/docs/_src/api/api/generator.md +++ b/docs/_src/api/api/generator.md @@ -445,4 +445,3 @@ Example: **Returns**: Dictionary containing query and Answers. - diff --git a/docs/_src/api/api/other_nodes.md b/docs/_src/api/api/other_nodes.md index 3d6ef93dd6..0f7507aa63 100644 --- a/docs/_src/api/api/other_nodes.md +++ b/docs/_src/api/api/other_nodes.md @@ -136,4 +136,3 @@ well. of values to group the `Document`s to. `Document`s whose metadata field is equal to the first value of the provided list will be routed to `"output_1"`, `Document`s whose metadata field is equal to the second value of the provided list will be routed to `"output_2"`, etc. - diff --git a/docs/_src/api/api/pipelines.md b/docs/_src/api/api/pipelines.md index 70be12c9b0..d65288c592 100644 --- a/docs/_src/api/api/pipelines.md +++ b/docs/_src/api/api/pipelines.md @@ -1974,4 +1974,3 @@ def run_batch(document_ids: List[str], top_k: int = 5) - `document_ids`: document ids - `top_k`: How many documents id to return against single document - diff --git a/docs/_src/api/api/preprocessor.md b/docs/_src/api/api/preprocessor.md index fe62a1b815..cdb1e999b4 100644 --- a/docs/_src/api/api/preprocessor.md +++ b/docs/_src/api/api/preprocessor.md @@ -148,4 +148,3 @@ def split(document: Union[dict, Document], Perform document splitting on a single document. This method can split on different units, at different lengths, with different strides. It can also respect sentence boundaries. Its exact functionality is defined by the parameters passed into PreProcessor.__init__(). Takes a single document as input and returns a list of documents. - diff --git a/docs/_src/api/api/primitives.md b/docs/_src/api/api/primitives.md index 604a15c76c..ba29c324d9 100644 --- a/docs/_src/api/api/primitives.md +++ b/docs/_src/api/api/primitives.md @@ -264,7 +264,7 @@ or, user-feedback from the Haystack REST API. **Arguments**: - `query`: the question (or query) for finding answers. -- `document`: +- `document`: - `answer`: the answer object. - `is_correct_answer`: whether the sample is positive or negative. - `is_correct_document`: in case of negative sample(is_correct_answer is False), there could be two cases; @@ -599,4 +599,3 @@ Loads the evaluation result from disk. Expects one csv file per node. See save() This method uses different default values than pd.read_csv() for the following parameters: header=0, converters=CONVERTERS where CONVERTERS is a dictionary mapping all array typed columns to ast.literal_eval. - diff --git a/docs/_src/api/api/pseudo_label_generator.md b/docs/_src/api/api/pseudo_label_generator.md index d0d62e807b..f6c60ee59c 100644 --- a/docs/_src/api/api/pseudo_label_generator.md +++ b/docs/_src/api/api/pseudo_label_generator.md @@ -33,14 +33,14 @@ For example: **Notes**: - + While the NLP researchers trained the default question [generation](https://huggingface.co/doc2query/msmarco-t5-base-v1) and the cross [encoder](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L-6-v2) models on the English language corpus, we can also use the language-specific question generation and cross-encoder models in the target language of our choice to apply GPL to documents in languages other than English. - + As of this writing, the German language question [generation](https://huggingface.co/ml6team/mt5-small-german-query-generation) and the cross [encoder](https://huggingface.co/ml6team/cross-encoder-mmarco-german-distilbert-base) models are @@ -194,4 +194,3 @@ dictionary contains the following keys: - pos_doc: Positive document for the given question. - neg_doc: Negative document for the given question. - score: The margin between the score for question-positive document pair and the score for question-negative document pair. - diff --git a/docs/_src/api/api/query_classifier.md b/docs/_src/api/api/query_classifier.md index de79384189..bc7b0ab690 100644 --- a/docs/_src/api/api/query_classifier.md +++ b/docs/_src/api/api/query_classifier.md @@ -35,17 +35,17 @@ and the further processing can be customized. You can define this by connecting |pipe.add_node(component=SklearnQueryClassifier(), name="QueryClassifier", inputs=["Query"]) |pipe.add_node(component=elastic_retriever, name="ElasticRetriever", inputs=["QueryClassifier.output_2"]) |pipe.add_node(component=dpr_retriever, name="DPRRetriever", inputs=["QueryClassifier.output_1"]) - + |# Keyword queries will use the ElasticRetriever |pipe.run("kubernetes aws") - + |# Semantic queries (questions, statements, sentences ...) will leverage the DPR retriever |pipe.run("How to manage kubernetes on aws") - + ``` - + Models: - + Pass your own `Sklearn` binary classification model or use one of the following pretrained ones: 1) Keywords vs. Questions/Statements (Default) query_classifier can be found [here](https://ext-models-haystack.s3.eu-central-1.amazonaws.com/gradboost_query_classifier/model.pickle) @@ -53,15 +53,15 @@ and the further processing can be customized. You can define this by connecting output_1 => question/statement output_2 => keyword query [Readme](https://ext-models-haystack.s3.eu-central-1.amazonaws.com/gradboost_query_classifier/readme.txt) - - + + 2) Questions vs. Statements query_classifier can be found [here](https://ext-models-haystack.s3.eu-central-1.amazonaws.com/gradboost_query_classifier_statements/model.pickle) query_vectorizer can be found [here](https://ext-models-haystack.s3.eu-central-1.amazonaws.com/gradboost_query_classifier_statements/vectorizer.pickle) output_1 => question output_2 => statement [Readme](https://ext-models-haystack.s3.eu-central-1.amazonaws.com/gradboost_query_classifier_statements/readme.txt) - + See also the [tutorial](https://haystack.deepset.ai/tutorials/pipelines) on pipelines. @@ -116,17 +116,17 @@ This node also supports zero-shot-classification. |pipe.add_node(component=TransformersQueryClassifier(), name="QueryClassifier", inputs=["Query"]) |pipe.add_node(component=elastic_retriever, name="ElasticRetriever", inputs=["QueryClassifier.output_2"]) |pipe.add_node(component=dpr_retriever, name="DPRRetriever", inputs=["QueryClassifier.output_1"]) - + |# Keyword queries will use the ElasticRetriever |pipe.run("kubernetes aws") - + |# Semantic queries (questions, statements, sentences ...) will leverage the DPR retriever |pipe.run("How to manage kubernetes on aws") - + ``` - + Models: - + Pass your own `Transformer` classification/zero-shot-classification model from file/huggingface or use one of the following pretrained ones hosted on Huggingface: 1) Keywords vs. Questions/Statements (Default) @@ -134,15 +134,15 @@ This node also supports zero-shot-classification. output_1 => question/statement output_2 => keyword query [Readme](https://ext-models-haystack.s3.eu-central-1.amazonaws.com/gradboost_query_classifier/readme.txt) - - + + 2) Questions vs. Statements `model_name_or_path`="shahrukhx01/question-vs-statement-classifier" output_1 => question output_2 => statement [Readme](https://ext-models-haystack.s3.eu-central-1.amazonaws.com/gradboost_query_classifier_statements/readme.txt) - - + + See also the [tutorial](https://haystack.deepset.ai/tutorials/pipelines) on pipelines. @@ -185,4 +185,3 @@ https://huggingface.co/transformers/main_classes/model.html#transformers.PreTrai A list containing torch device objects and/or strings is supported (For example [torch.device('cuda:0'), "mps", "cuda:1"]). When specifying `use_gpu=False` the devices parameter is not used and a single cpu device is used for inference. - diff --git a/docs/_src/api/api/question_generator.md b/docs/_src/api/api/question_generator.md index faaa14fe02..4628439595 100644 --- a/docs/_src/api/api/question_generator.md +++ b/docs/_src/api/api/question_generator.md @@ -83,4 +83,3 @@ Generates questions for a list of strings or a list of lists of strings. - `texts`: List of str or list of list of str. - `batch_size`: Number of texts to process at a time. - diff --git a/docs/_src/api/api/ranker.md b/docs/_src/api/api/ranker.md index 0161b17368..5196cd9d62 100644 --- a/docs/_src/api/api/ranker.md +++ b/docs/_src/api/api/ranker.md @@ -194,4 +194,3 @@ Returns lists of Documents sorted by (desc.) similarity with the corresponding q - `documents`: Single list of Documents or list of lists of Documents to be reranked. - `top_k`: The maximum number of documents to return per Document list. - `batch_size`: Number of Documents to process at a time. - diff --git a/docs/_src/api/api/reader.md b/docs/_src/api/api/reader.md index 7da25f1967..1c26f95b28 100644 --- a/docs/_src/api/api/reader.md +++ b/docs/_src/api/api/reader.md @@ -1110,4 +1110,3 @@ of content_type ``'table'``. **Returns**: Dict containing query and answers - diff --git a/docs/_src/api/api/retriever.md b/docs/_src/api/api/retriever.md index 73a178e46c..1295cb1831 100644 --- a/docs/_src/api/api/retriever.md +++ b/docs/_src/api/api/retriever.md @@ -2124,4 +2124,3 @@ Generate formatted dictionary output with text answer and additional info **Arguments**: - `result`: The result of a SPARQL query as retrieved from the knowledge graph - diff --git a/docs/_src/api/api/summarizer.md b/docs/_src/api/api/summarizer.md index d91840de00..7d66850505 100644 --- a/docs/_src/api/api/summarizer.md +++ b/docs/_src/api/api/summarizer.md @@ -189,4 +189,3 @@ If set to "True", all docs of a document list will be joined to a single string that will then be summarized. Important: The summary will depend on the order of the supplied documents! - `batch_size`: Number of Documents to process at a time. - diff --git a/docs/_src/api/api/translator.md b/docs/_src/api/api/translator.md index 50ab26fd7e..7e4caf3411 100644 --- a/docs/_src/api/api/translator.md +++ b/docs/_src/api/api/translator.md @@ -167,4 +167,3 @@ Run the actual translation. You can supply a single query, a list of queries or - `queries`: Single query or list of queries. - `documents`: List of documents or list of lists of documets. - `batch_size`: Not applicable. - diff --git a/docs/_src/api/api/utils.md b/docs/_src/api/api/utils.md index 6e78382381..3f36acb186 100644 --- a/docs/_src/api/api/utils.md +++ b/docs/_src/api/api/utils.md @@ -388,4 +388,3 @@ prediction head. Each dictionary contains the metrics and reports generated duri A tuple (stopprocessing, savemodel, eval_value) indicating if processing should be stopped and if the current model should get saved and the evaluation value used. - diff --git a/docs/_src/api/openapi/openapi-1.10.0rc0.json b/docs/_src/api/openapi/openapi-1.10.0rc0.json index 52f302eda1..411bec60a8 100644 --- a/docs/_src/api/openapi/openapi-1.10.0rc0.json +++ b/docs/_src/api/openapi/openapi-1.10.0rc0.json @@ -1025,4 +1025,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.11.0rc0.json b/docs/_src/api/openapi/openapi-1.11.0rc0.json index 0e515d2a9c..b2866e142d 100644 --- a/docs/_src/api/openapi/openapi-1.11.0rc0.json +++ b/docs/_src/api/openapi/openapi-1.11.0rc0.json @@ -1021,4 +1021,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.12.0rc0.json b/docs/_src/api/openapi/openapi-1.12.0rc0.json index 6482c2d9d0..4b76eca16c 100644 --- a/docs/_src/api/openapi/openapi-1.12.0rc0.json +++ b/docs/_src/api/openapi/openapi-1.12.0rc0.json @@ -1033,4 +1033,4 @@ "python" ] } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.2.0.json b/docs/_src/api/openapi/openapi-1.2.0.json index 36971bd89f..aa3a5e2a0a 100644 --- a/docs/_src/api/openapi/openapi-1.2.0.json +++ b/docs/_src/api/openapi/openapi-1.2.0.json @@ -831,4 +831,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.2.1rc0.json b/docs/_src/api/openapi/openapi-1.2.1rc0.json index 5958d6a11f..f77541b0ee 100644 --- a/docs/_src/api/openapi/openapi-1.2.1rc0.json +++ b/docs/_src/api/openapi/openapi-1.2.1rc0.json @@ -824,4 +824,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.3.0.json b/docs/_src/api/openapi/openapi-1.3.0.json index cd388129fb..56d3720021 100644 --- a/docs/_src/api/openapi/openapi-1.3.0.json +++ b/docs/_src/api/openapi/openapi-1.3.0.json @@ -831,4 +831,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.3.1rc0.json b/docs/_src/api/openapi/openapi-1.3.1rc0.json index 8fff7c9626..7a85655de7 100644 --- a/docs/_src/api/openapi/openapi-1.3.1rc0.json +++ b/docs/_src/api/openapi/openapi-1.3.1rc0.json @@ -889,4 +889,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.4.0.json b/docs/_src/api/openapi/openapi-1.4.0.json index 9dd0363856..cc161e312d 100644 --- a/docs/_src/api/openapi/openapi-1.4.0.json +++ b/docs/_src/api/openapi/openapi-1.4.0.json @@ -889,4 +889,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.4.1rc0.json b/docs/_src/api/openapi/openapi-1.4.1rc0.json index 1f61a21ec4..689dbabdb3 100644 --- a/docs/_src/api/openapi/openapi-1.4.1rc0.json +++ b/docs/_src/api/openapi/openapi-1.4.1rc0.json @@ -890,4 +890,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.5.0.json b/docs/_src/api/openapi/openapi-1.5.0.json index fd07ddd0d5..5e92063ce7 100644 --- a/docs/_src/api/openapi/openapi-1.5.0.json +++ b/docs/_src/api/openapi/openapi-1.5.0.json @@ -889,4 +889,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.5.1rc0.json b/docs/_src/api/openapi/openapi-1.5.1rc0.json index 9ff281d5a1..2150cee473 100644 --- a/docs/_src/api/openapi/openapi-1.5.1rc0.json +++ b/docs/_src/api/openapi/openapi-1.5.1rc0.json @@ -890,4 +890,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.6.0.json b/docs/_src/api/openapi/openapi-1.6.0.json index 5872045250..48ee1dfcb6 100644 --- a/docs/_src/api/openapi/openapi-1.6.0.json +++ b/docs/_src/api/openapi/openapi-1.6.0.json @@ -890,4 +890,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.6.1rc0.json b/docs/_src/api/openapi/openapi-1.6.1rc0.json index fcc336df71..a3c4d75b8c 100644 --- a/docs/_src/api/openapi/openapi-1.6.1rc0.json +++ b/docs/_src/api/openapi/openapi-1.6.1rc0.json @@ -883,4 +883,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.7.0.json b/docs/_src/api/openapi/openapi-1.7.0.json index 209a1723ad..7471bf6a04 100644 --- a/docs/_src/api/openapi/openapi-1.7.0.json +++ b/docs/_src/api/openapi/openapi-1.7.0.json @@ -883,4 +883,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.7.1.json b/docs/_src/api/openapi/openapi-1.7.1.json index b2ce05533f..2e56e9d006 100644 --- a/docs/_src/api/openapi/openapi-1.7.1.json +++ b/docs/_src/api/openapi/openapi-1.7.1.json @@ -883,4 +883,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.7.1rc0.json b/docs/_src/api/openapi/openapi-1.7.1rc0.json index b833a556fe..ab589797da 100644 --- a/docs/_src/api/openapi/openapi-1.7.1rc0.json +++ b/docs/_src/api/openapi/openapi-1.7.1rc0.json @@ -883,4 +883,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.7.2.json b/docs/_src/api/openapi/openapi-1.7.2.json index 2f5d7cfa1c..eaafe049a9 100644 --- a/docs/_src/api/openapi/openapi-1.7.2.json +++ b/docs/_src/api/openapi/openapi-1.7.2.json @@ -883,4 +883,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.7.2rc0.json b/docs/_src/api/openapi/openapi-1.7.2rc0.json index 295a2cb3b2..58449f49b2 100644 --- a/docs/_src/api/openapi/openapi-1.7.2rc0.json +++ b/docs/_src/api/openapi/openapi-1.7.2rc0.json @@ -883,4 +883,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.7.3rc0.json b/docs/_src/api/openapi/openapi-1.7.3rc0.json index b9d3f5dd9a..a65481d02a 100644 --- a/docs/_src/api/openapi/openapi-1.7.3rc0.json +++ b/docs/_src/api/openapi/openapi-1.7.3rc0.json @@ -883,4 +883,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.8.0.json b/docs/_src/api/openapi/openapi-1.8.0.json index 86156cf559..45008a5db4 100644 --- a/docs/_src/api/openapi/openapi-1.8.0.json +++ b/docs/_src/api/openapi/openapi-1.8.0.json @@ -883,4 +883,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/openapi/openapi-1.8.1rc0.json b/docs/_src/api/openapi/openapi-1.8.1rc0.json index 2ad4d3dc22..1f97fbd0d8 100644 --- a/docs/_src/api/openapi/openapi-1.8.1rc0.json +++ b/docs/_src/api/openapi/openapi-1.8.1rc0.json @@ -1025,4 +1025,4 @@ } } } -} \ No newline at end of file +} diff --git a/docs/_src/api/pydoc/answer-generator.yml b/docs/_src/api/pydoc/answer-generator.yml index 3ac7cd95e6..2197e90525 100644 --- a/docs/_src/api/pydoc/answer-generator.yml +++ b/docs/_src/api/pydoc/answer-generator.yml @@ -5,7 +5,7 @@ loaders: ignore_when_discovered: ['__init__'] processors: - type: filter - expression: + expression: documented_only: true do_not_filter_modules: false skip_empty_modules: true @@ -24,5 +24,3 @@ renderer: add_method_class_prefix: true add_member_class_prefix: false filename: answer_generator_api.md - - diff --git a/docs/_src/api/pydoc/translator.yml b/docs/_src/api/pydoc/translator.yml index 0cb9eacc45..fb28220af2 100644 --- a/docs/_src/api/pydoc/translator.yml +++ b/docs/_src/api/pydoc/translator.yml @@ -5,7 +5,7 @@ loaders: ignore_when_discovered: ['__init__'] processors: - type: filter - expression: + expression: documented_only: true do_not_filter_modules: false skip_empty_modules: true @@ -23,4 +23,4 @@ renderer: descriptive_module_title: true add_method_class_prefix: true add_member_class_prefix: false - filename: translator_api.md \ No newline at end of file + filename: translator_api.md diff --git a/docs/_src/api/pydoc/utils.yml b/docs/_src/api/pydoc/utils.yml index 1bae162fce..55f2ce870b 100644 --- a/docs/_src/api/pydoc/utils.yml +++ b/docs/_src/api/pydoc/utils.yml @@ -23,4 +23,4 @@ renderer: descriptive_module_title: true add_method_class_prefix: true add_member_class_prefix: false - filename: utils_api.md \ No newline at end of file + filename: utils_api.md diff --git a/docs/_src/benchmarks/reader_performance.json b/docs/_src/benchmarks/reader_performance.json index 4c5b53352c..2a0d5e1e81 100644 --- a/docs/_src/benchmarks/reader_performance.json +++ b/docs/_src/benchmarks/reader_performance.json @@ -41,4 +41,4 @@ "Model": "distilBERT" } ] -} \ No newline at end of file +} diff --git a/docs/_src/benchmarks/reader_results.md b/docs/_src/benchmarks/reader_results.md index 318bfebc1e..7ffe7f7b90 100644 --- a/docs/_src/benchmarks/reader_results.md +++ b/docs/_src/benchmarks/reader_results.md @@ -5,4 +5,4 @@ | 2 | 70.0826 | 73.4981 | 95.5335 | 5 | 105.557 | 0.00889576 | 56.598 | 63.4371 | 91.0564 | 72.1228 | 84.4785 | 5926 | 83.5354 | 83.5354 | 100 | 5940 | 116.998 | deepset/bert-base-cased-squad2 | | | 3 | 83.6929 | 87.3504 | 98.0785 | 5 | 284.209 | 0.0239515 | 75.1941 | 82.5177 | 96.1525 | 82.3321 | 91.8921 | 5926 | 92.1717 | 92.1717 | 100 | 5940 | 43.454 | deepset/roberta-large-squad2 | | | 4 | 79.5045 | 82.2939 | 97.5223 | 5 | 103.885 | 0.00875486 | 71.1104 | 76.6958 | 95.0388 | 81.7246 | 90.891 | 5926 | 87.8788 | 87.8788 | 100 | 5940 | 118.881 | deepset/roberta-base-squad2-distilled | | -| 5 | 38.5387 | 43.3403 | 95.4323 | 5 | 62.2323 | 0.00524459 | 74.5359 | 84.1505 | 90.8539 | 75.0928 | 85.2126 | 5926 | 2.62626 | 2.62626 | 100 | 5940 | 198.45 | distilbert-base-uncased-distilled-squad | | \ No newline at end of file +| 5 | 38.5387 | 43.3403 | 95.4323 | 5 | 62.2323 | 0.00524459 | 74.5359 | 84.1505 | 90.8539 | 75.0928 | 85.2126 | 5926 | 2.62626 | 2.62626 | 100 | 5940 | 198.45 | distilbert-base-uncased-distilled-squad | | diff --git a/docs/_src/benchmarks/retriever_index_results.md b/docs/_src/benchmarks/retriever_index_results.md index 37954fe2a1..03e0a42446 100644 --- a/docs/_src/benchmarks/retriever_index_results.md +++ b/docs/_src/benchmarks/retriever_index_results.md @@ -31,4 +31,4 @@ | 11 | dpr | opensearch_hnsw | 10000 | 121.491 | 82.3109 | 2022-09-17 08:34:11.508717 | | | 3 | dpr | opensearch_hnsw | 1000 | 12.356 | 80.9326 | 2022-09-17 08:23:36.852546 | | | 19 | dpr | opensearch_hnsw | 100000 | 1242.96 | 80.4531 | 2022-09-17 09:35:31.609351 | | -| 27 | dpr | opensearch_hnsw | 500000 | 6237.19 | 80.1643 | 2022-09-17 14:59:57.763007 | | \ No newline at end of file +| 27 | dpr | opensearch_hnsw | 500000 | 6237.19 | 80.1643 | 2022-09-17 14:59:57.763007 | | diff --git a/docs/_src/benchmarks/retriever_map.json b/docs/_src/benchmarks/retriever_map.json index b41a997490..df37f78fcd 100644 --- a/docs/_src/benchmarks/retriever_map.json +++ b/docs/_src/benchmarks/retriever_map.json @@ -181,4 +181,4 @@ "map": 80.861372282341 } ] -} \ No newline at end of file +} diff --git a/docs/_src/benchmarks/retriever_performance.json b/docs/_src/benchmarks/retriever_performance.json index dcac2349bd..dd511f686c 100644 --- a/docs/_src/benchmarks/retriever_performance.json +++ b/docs/_src/benchmarks/retriever_performance.json @@ -78,4 +78,4 @@ "map": 86.53719331739565 } ] -} \ No newline at end of file +} diff --git a/docs/_src/benchmarks/retriever_query_results.md b/docs/_src/benchmarks/retriever_query_results.md index fc86f7436d..e6b20a9ba9 100644 --- a/docs/_src/benchmarks/retriever_query_results.md +++ b/docs/_src/benchmarks/retriever_query_results.md @@ -31,4 +31,4 @@ | 11 | dpr | opensearch_hnsw | 10000 | 5637 | 181.917 | 30.9866 | 0.032272 | 97.4987 | 89.871 | 10 | 2022-09-17 21:42:16.601719 | | | 3 | dpr | opensearch_hnsw | 1000 | 1064 | 29.8264 | 35.673 | 0.0280324 | 99.1541 | 92.9511 | 10 | 2022-09-17 21:23:12.487039 | | | 19 | dpr | opensearch_hnsw | 100000 | 5637 | 327.224 | 17.2268 | 0.0580493 | 95.7779 | 86.5372 | 10 | 2022-09-17 22:36:46.502520 | | -| 27 | dpr | opensearch_hnsw | 500000 | 5637 | 477.335 | 11.8093 | 0.0846789 | 93.0814 | 80.8614 | 10 | 2022-09-18 01:53:29.735540 | | \ No newline at end of file +| 27 | dpr | opensearch_hnsw | 500000 | 5637 | 477.335 | 11.8093 | 0.0846789 | 93.0814 | 80.8614 | 10 | 2022-09-18 01:53:29.735540 | | diff --git a/docs/_src/benchmarks/retriever_speed.json b/docs/_src/benchmarks/retriever_speed.json index a153baba0d..66727912e0 100644 --- a/docs/_src/benchmarks/retriever_speed.json +++ b/docs/_src/benchmarks/retriever_speed.json @@ -181,4 +181,4 @@ "query_speed": 11.809321812785312 } ] -} \ No newline at end of file +} diff --git a/docs/release_docs.sh b/docs/release_docs.sh index 9ad53eca72..ede861d8ff 100755 --- a/docs/release_docs.sh +++ b/docs/release_docs.sh @@ -6,4 +6,4 @@ # Create folder for new docs veresion mkdir "$1" -cp -a make.bat Makefile _src "$1" \ No newline at end of file +cp -a make.bat Makefile _src "$1" diff --git a/docs/v0.10.0/_src/api/_static/floating_sidebar.css b/docs/v0.10.0/_src/api/_static/floating_sidebar.css index e59adc6722..78d1423356 100644 --- a/docs/v0.10.0/_src/api/_static/floating_sidebar.css +++ b/docs/v0.10.0/_src/api/_static/floating_sidebar.css @@ -26,4 +26,4 @@ div.sphinxsidebar .logo img { div.sphinxsidebar .download a img { vertical-align: middle; -} \ No newline at end of file +} diff --git a/docs/v0.10.0/_src/api/_templates/xxlayout.html b/docs/v0.10.0/_src/api/_templates/xxlayout.html index de71588332..47ec94d1cf 100644 --- a/docs/v0.10.0/_src/api/_templates/xxlayout.html +++ b/docs/v0.10.0/_src/api/_templates/xxlayout.html @@ -43,4 +43,4 @@ }); {#- endif #} -{% endblock %} \ No newline at end of file +{% endblock %} diff --git a/docs/v0.10.0/_src/api/api/classifier.md b/docs/v0.10.0/_src/api/api/classifier.md index b99ee585c5..7f37fcd81f 100644 --- a/docs/v0.10.0/_src/api/api/classifier.md +++ b/docs/v0.10.0/_src/api/api/classifier.md @@ -196,4 +196,3 @@ Returns list of Document enriched with class label and probability, which are st **Returns**: List of Document with class probabilities in meta field - diff --git a/docs/v0.10.0/_src/api/api/crawler.md b/docs/v0.10.0/_src/api/api/crawler.md index dcdb6cf929..fe5593d62f 100644 --- a/docs/v0.10.0/_src/api/api/crawler.md +++ b/docs/v0.10.0/_src/api/api/crawler.md @@ -34,8 +34,8 @@ Init object with basic params for crawling (can be overwritten later). - `output_dir`: Path for the directory to store files - `urls`: List of http(s) address(es) (can also be supplied later when calling crawl()) - `crawler_depth`: How many sublinks to follow from the initial list of URLs. Current options: - 0: Only initial list of urls - 1: Follow links found on the initial URLs (but no further) + 0: Only initial list of urls + 1: Follow links found on the initial URLs (but no further) - `filter_urls`: Optional list of regular expressions that the crawled URLs must comply with. All URLs not matching at least one of the regular expressions will be dropped. - `overwrite_existing_files`: Whether to overwrite existing files in output_dir with new content @@ -92,4 +92,3 @@ Method to be executed when the Crawler is used as a Node within a Haystack pipel **Returns**: Tuple({"paths": List of filepaths, ...}, Name of output edge) - diff --git a/docs/v0.10.0/_src/api/api/document_store.md b/docs/v0.10.0/_src/api/api/document_store.md index 3e12d5f05b..8329ed8587 100644 --- a/docs/v0.10.0/_src/api/api/document_store.md +++ b/docs/v0.10.0/_src/api/api/document_store.md @@ -1014,7 +1014,7 @@ the vector embeddings are indexed in a FAISS Index. - `index`: Name of index in document store to use. - `similarity`: The similarity function used to compare document vectors. 'dot_product' is the default since it is more performant with DPR embeddings. 'cosine' is recommended if you are using a Sentence-Transformer model. - In both cases, the returned values in Document.score are normalized to be in range [0,1]: + In both cases, the returned values in Document.score are normalized to be in range [0,1]: For `dot_product`: expit(np.asarray(raw_score / 100)) FOr `cosine`: (raw_score + 1) / 2 - `embedding_field`: Name of field containing an embedding vector. @@ -1188,7 +1188,7 @@ Save FAISS Index to the specified file. - `config_path`: Path to save the initial configuration parameters to. Defaults to the same as the file path, save the extension (.json). This file contains all the parameters passed to FAISSDocumentStore() - at creation time (for example the SQL path, vector_dim, etc), and will be + at creation time (for example the SQL path, vector_dim, etc), and will be used by the `load` method to restore the index with the appropriate configuration. **Returns**: @@ -1215,7 +1215,7 @@ Note: In order to have a correct mapping from FAISS to SQL, - `sql_url`: Connection string to the SQL database that contains your docs and metadata. Overrides the value defined in the `faiss_init_params_path` file, if present - `index`: Index name to load the FAISS index as. It must match the index name used for - when creating the FAISS index. Overrides the value defined in the + when creating the FAISS index. Overrides the value defined in the `faiss_init_params_path` file, if present **Returns**: @@ -1526,8 +1526,8 @@ Weaviate is a cloud-native, modular, real-time vector search engine built to sca Some of the key differences in contrast to FAISS & Milvus: 1. Stores everything in one place: documents, meta data and vectors - so less network overhead when scaling this up -2. Allows combination of vector search and scalar filtering, i.e. you can filter for a certain tag and do dense retrieval on that subset -3. Has less variety of ANN algorithms, as of now only HNSW. +2. Allows combination of vector search and scalar filtering, i.e. you can filter for a certain tag and do dense retrieval on that subset +3. Has less variety of ANN algorithms, as of now only HNSW. Weaviate python client is used to connect to the server, more details are here https://weaviate-python-client.readthedocs.io/en/docs/weaviate.html @@ -1779,4 +1779,3 @@ Delete documents in an index. All documents are deleted if no filters are passed **Returns**: None - diff --git a/docs/v0.10.0/_src/api/api/evaluation.md b/docs/v0.10.0/_src/api/api/evaluation.md index 90d106b225..53fedce773 100644 --- a/docs/v0.10.0/_src/api/api/evaluation.md +++ b/docs/v0.10.0/_src/api/api/evaluation.md @@ -123,4 +123,3 @@ Returns per QA pair a) the similarity of the most likely prediction (top 1) to a :return: top_1_sas, top_k_sas - diff --git a/docs/v0.10.0/_src/api/api/file_converter.md b/docs/v0.10.0/_src/api/api/file_converter.md index e23bddbce9..3f9a4508c4 100644 --- a/docs/v0.10.0/_src/api/api/file_converter.md +++ b/docs/v0.10.0/_src/api/api/file_converter.md @@ -337,4 +337,3 @@ supplied meta data like author, url, external IDs can be supplied as a dictionar not one of the valid languages, then it might likely be encoding error resulting in garbled text. - `encoding`: Select the file encoding (default is `utf-8`) - diff --git a/docs/v0.10.0/_src/api/api/generate_docstrings.sh b/docs/v0.10.0/_src/api/api/generate_docstrings.sh index 86a52e0ac2..9e84a8cf69 100755 --- a/docs/v0.10.0/_src/api/api/generate_docstrings.sh +++ b/docs/v0.10.0/_src/api/api/generate_docstrings.sh @@ -18,4 +18,3 @@ pydoc-markdown pydoc-markdown-evaluation.yml pydoc-markdown pydoc-markdown-ranker.yml pydoc-markdown pydoc-markdown-question-generator.yml pydoc-markdown pydoc-markdown-classifier.yml - diff --git a/docs/v0.10.0/_src/api/api/generator.md b/docs/v0.10.0/_src/api/api/generator.md index 6cb1309561..eef96d4954 100644 --- a/docs/v0.10.0/_src/api/api/generator.md +++ b/docs/v0.10.0/_src/api/api/generator.md @@ -155,8 +155,8 @@ GenerationMixin can be used by Seq2SeqGenerator. Moreover, as language models prepare model input in their specific encoding, each model specified with model_name_or_path parameter in this Seq2SeqGenerator should have an accompanying model input converter that takes care of prefixes, separator tokens etc. -By default, we provide model input converters for a few well-known seq2seq language models (e.g. ELI5). -It is the responsibility of Seq2SeqGenerator user to ensure an appropriate model input converter +By default, we provide model input converters for a few well-known seq2seq language models (e.g. ELI5). +It is the responsibility of Seq2SeqGenerator user to ensure an appropriate model input converter is either already registered or specified on a per-model basis in the Seq2SeqGenerator constructor. For mode details on custom model input converters refer to _BartEli5Converter @@ -229,4 +229,3 @@ These document can be retrieved via the Retriever or supplied directly via predi **Returns**: Generated answers - diff --git a/docs/v0.10.0/_src/api/api/graph_retriever.md b/docs/v0.10.0/_src/api/api/graph_retriever.md index d8b1be7804..a24ead4dcf 100644 --- a/docs/v0.10.0/_src/api/api/graph_retriever.md +++ b/docs/v0.10.0/_src/api/api/graph_retriever.md @@ -55,4 +55,3 @@ Generate formatted dictionary output with text answer and additional info **Arguments**: - `result`: The result of a SPARQL query as retrieved from the knowledge graph - diff --git a/docs/v0.10.0/_src/api/api/knowledge_graph.md b/docs/v0.10.0/_src/api/api/knowledge_graph.md index 08f07b7e9b..bd4a18de94 100644 --- a/docs/v0.10.0/_src/api/api/knowledge_graph.md +++ b/docs/v0.10.0/_src/api/api/knowledge_graph.md @@ -152,4 +152,3 @@ Execute a SPARQL query on the given index in the GraphDB instance **Returns**: query result - diff --git a/docs/v0.10.0/_src/api/api/pipelines.md b/docs/v0.10.0/_src/api/api/pipelines.md index f496e0e9a6..766868339d 100644 --- a/docs/v0.10.0/_src/api/api/pipelines.md +++ b/docs/v0.10.0/_src/api/api/pipelines.md @@ -551,17 +551,17 @@ and the further processing can be customized. You can define this by connecting |pipe.add_node(component=SklearnQueryClassifier(), name="QueryClassifier", inputs=["Query"]) |pipe.add_node(component=elastic_retriever, name="ElasticRetriever", inputs=["QueryClassifier.output_2"]) |pipe.add_node(component=dpr_retriever, name="DPRRetriever", inputs=["QueryClassifier.output_1"]) - + |# Keyword queries will use the ElasticRetriever |pipe.run("kubernetes aws") - + |# Semantic queries (questions, statements, sentences ...) will leverage the DPR retriever |pipe.run("How to manage kubernetes on aws") - + ``` - + Models: - + Pass your own `Sklearn` binary classification model or use one of the following pretrained ones: 1) Keywords vs. Questions/Statements (Default) query_classifier can be found [here](https://ext-models-haystack.s3.eu-central-1.amazonaws.com/gradboost_query_classifier/model.pickle) @@ -569,15 +569,15 @@ and the further processing can be customized. You can define this by connecting output_1 => question/statement output_2 => keyword query [Readme](https://ext-models-haystack.s3.eu-central-1.amazonaws.com/gradboost_query_classifier/readme.txt) - - + + 2) Questions vs. Statements query_classifier can be found [here](https://ext-models-haystack.s3.eu-central-1.amazonaws.com/gradboost_query_classifier_statements/model.pickle) query_vectorizer can be found [here](https://ext-models-haystack.s3.eu-central-1.amazonaws.com/gradboost_query_classifier_statements/vectorizer.pickle) output_1 => question output_2 => statement [Readme](https://ext-models-haystack.s3.eu-central-1.amazonaws.com/gradboost_query_classifier_statements/readme.txt) - + See also the [tutorial](https://haystack.deepset.ai/tutorials/pipelines) on pipelines. @@ -615,31 +615,31 @@ and the further processing can be customized. You can define this by connecting |pipe.add_node(component=TransformersQueryClassifier(), name="QueryClassifier", inputs=["Query"]) |pipe.add_node(component=elastic_retriever, name="ElasticRetriever", inputs=["QueryClassifier.output_2"]) |pipe.add_node(component=dpr_retriever, name="DPRRetriever", inputs=["QueryClassifier.output_1"]) - + |# Keyword queries will use the ElasticRetriever |pipe.run("kubernetes aws") - + |# Semantic queries (questions, statements, sentences ...) will leverage the DPR retriever |pipe.run("How to manage kubernetes on aws") - + ``` - + Models: - + Pass your own `Transformer` binary classification model from file/huggingface or use one of the following pretrained ones hosted on Huggingface: 1) Keywords vs. Questions/Statements (Default) model_name_or_path="shahrukhx01/bert-mini-finetune-question-detection" output_1 => question/statement output_2 => keyword query [Readme](https://ext-models-haystack.s3.eu-central-1.amazonaws.com/gradboost_query_classifier/readme.txt) - - + + 2) Questions vs. Statements `model_name_or_path`="shahrukhx01/question-vs-statement-classifier" output_1 => question output_2 => statement [Readme](https://ext-models-haystack.s3.eu-central-1.amazonaws.com/gradboost_query_classifier_statements/readme.txt) - + See also the [tutorial](https://haystack.deepset.ai/tutorials/pipelines) on pipelines. @@ -867,4 +867,3 @@ This pipeline can be helpful if you already show a relevant document to your end - `document_ids`: document ids - `top_k`: How many documents id to return against single document - diff --git a/docs/v0.10.0/_src/api/api/preprocessor.md b/docs/v0.10.0/_src/api/api/preprocessor.md index 08dfb51919..9ff39ce916 100644 --- a/docs/v0.10.0/_src/api/api/preprocessor.md +++ b/docs/v0.10.0/_src/api/api/preprocessor.md @@ -225,4 +225,3 @@ clean_wiki_text(text: str) -> str Clean wikipedia text by removing multiple new lines, removing extremely short lines, adding paragraph breaks and removing empty paragraphs - diff --git a/docs/v0.10.0/_src/api/api/pydoc-markdown-ranker.yml b/docs/v0.10.0/_src/api/api/pydoc-markdown-ranker.yml index 0ed0e01389..fcfdd8c4b8 100644 --- a/docs/v0.10.0/_src/api/api/pydoc-markdown-ranker.yml +++ b/docs/v0.10.0/_src/api/api/pydoc-markdown-ranker.yml @@ -16,4 +16,3 @@ renderer: add_method_class_prefix: false add_member_class_prefix: false filename: ranker.md - diff --git a/docs/v0.10.0/_src/api/api/question_generator.md b/docs/v0.10.0/_src/api/api/question_generator.md index 92bebd0cc8..68fd8d0b64 100644 --- a/docs/v0.10.0/_src/api/api/question_generator.md +++ b/docs/v0.10.0/_src/api/api/question_generator.md @@ -27,4 +27,3 @@ Uses the valhalla/t5-base-e2e-qg model by default. This class supports any quest implemented as a Seq2SeqLM in HuggingFace Transformers. Note that this style of question generation (where the only input is a document) is sometimes referred to as end-to-end question generation. Answer-supervised question generation is not currently supported. - diff --git a/docs/v0.10.0/_src/api/api/ranker.md b/docs/v0.10.0/_src/api/api/ranker.md index d3019a7616..74819cf0c8 100644 --- a/docs/v0.10.0/_src/api/api/ranker.md +++ b/docs/v0.10.0/_src/api/api/ranker.md @@ -215,4 +215,3 @@ Returns list of Document sorted by (desc.) TextPairClassification similarity wit **Returns**: List of Document - diff --git a/docs/v0.10.0/_src/api/api/reader.md b/docs/v0.10.0/_src/api/api/reader.md index 6361744f5d..59906bc174 100644 --- a/docs/v0.10.0/_src/api/api/reader.md +++ b/docs/v0.10.0/_src/api/api/reader.md @@ -429,4 +429,3 @@ Example: **Returns**: Dict containing query and answers - diff --git a/docs/v0.10.0/_src/api/api/retriever.md b/docs/v0.10.0/_src/api/api/retriever.md index a7bc7c517b..eebfe923b8 100644 --- a/docs/v0.10.0/_src/api/api/retriever.md +++ b/docs/v0.10.0/_src/api/api/retriever.md @@ -280,7 +280,7 @@ The checkpoint format matches huggingface transformers' model format {"text": "my text", "meta": {"name": "my title"}}. - `use_fast_tokenizers`: Whether to use fast Rust tokenizers - `infer_tokenizer_classes`: Whether to infer tokenizer class from the model config / name. - If `False`, the class always loads `DPRQuestionEncoderTokenizer` and `DPRContextEncoderTokenizer`. + If `False`, the class always loads `DPRQuestionEncoderTokenizer` and `DPRContextEncoderTokenizer`. - `similarity_function`: Which function to apply for calculating the similarity of query and passage embeddings during training. Options: `dot_product` (Default) or `cosine` - `global_loss_buffer_size`: Buffer size for all_gather() in DDP. @@ -543,4 +543,3 @@ Create embeddings for a list of passages. **Returns**: Embeddings, one per input passage - diff --git a/docs/v0.10.0/_src/api/api/summarizer.md b/docs/v0.10.0/_src/api/api/summarizer.md index df77bbb097..180ebf29e7 100644 --- a/docs/v0.10.0/_src/api/api/summarizer.md +++ b/docs/v0.10.0/_src/api/api/summarizer.md @@ -129,4 +129,3 @@ These document can for example be retrieved via the Retriever. List of Documents, where Document.text contains the summarization and Document.meta["context"] the original, not summarized text - diff --git a/docs/v0.10.0/_src/api/api/translator.md b/docs/v0.10.0/_src/api/api/translator.md index a2ff47cc85..aa60ccacbd 100644 --- a/docs/v0.10.0/_src/api/api/translator.md +++ b/docs/v0.10.0/_src/api/api/translator.md @@ -98,5 +98,4 @@ Run the actual translation. You can supply a query or a list of documents. Whate - `query`: The query string to translate - `documents`: The documents to translate -- `dict_key`: - +- `dict_key`: diff --git a/docs/v0.10.0/_src/benchmarks/farm_per_component.html b/docs/v0.10.0/_src/benchmarks/farm_per_component.html index 6a9d3d5cea..80ce118790 100644 --- a/docs/v0.10.0/_src/benchmarks/farm_per_component.html +++ b/docs/v0.10.0/_src/benchmarks/farm_per_component.html @@ -45,4 +45,3 @@