dfs_code = r""" def dfs(visited, graph, node): #function for dfs if node not in visited: print (node) visited.add(node) for neighbour in graph[node]: dfs(visited, graph, neighbour) """ function_code = r""" def write_documents(self, documents: Union[List[dict], List[Document]], index: Optional[str] = None, batch_size: int = 10_000, duplicate_documents: Optional[str] = None): if index and not self.client.indices.exists(index=index): self._create_document_index(index) if index is None: index = self.index duplicate_documents = duplicate_documents or self.duplicate_documents assert duplicate_documents in self.duplicate_documents_options, f"duplicate_documents parameter must be {', '.join(self.duplicate_documents_options)}" field_map = self._create_document_field_map() document_objects = [Document.from_dict(d, field_map=field_map) if isinstance(d, dict) else d for d in documents] document_objects = self._handle_duplicate_documents(documents=document_objects, index=index, duplicate_documents=duplicate_documents) documents_to_index = [] for doc in document_objects: _doc = { "_op_type": "index" if duplicate_documents == 'overwrite' else "create", "_index": index, **doc.to_dict(field_map=self._create_document_field_map()) } # type: Dict[str, Any] # cast embedding type as ES cannot deal with np.array if _doc[self.embedding_field] is not None: if type(_doc[self.embedding_field]) == np.ndarray: _doc[self.embedding_field] = _doc[self.embedding_field].tolist() # rename id for elastic _doc["_id"] = str(_doc.pop("id")) # don't index query score and empty fields _ = _doc.pop("score", None) _doc = {k:v for k,v in _doc.items() if v is not None} # In order to have a flat structure in elastic + similar behaviour to the other DocumentStores, # we "unnest" all value within "meta" if "meta" in _doc.keys(): for k, v in _doc["meta"].items(): _doc[k] = v _doc.pop("meta") documents_to_index.append(_doc) # Pass batch_size number of documents to bulk if len(documents_to_index) % batch_size == 0: bulk(self.client, documents_to_index, request_timeout=300, refresh=self.refresh_type) documents_to_index = [] if documents_to_index: bulk(self.client, documents_to_index, request_timeout=300, refresh=self.refresh_type) """ real_docstring = r""" Indexes documents for later queries in Elasticsearch. Behaviour if a document with the same ID already exists in ElasticSearch: a) (Default) Throw Elastic's standard error message for duplicate IDs. b) If `self.update_existing_documents=True` for DocumentStore: Overwrite existing documents. (This is only relevant if you pass your own ID when initializing a `Document`. If don't set custom IDs for your Documents or just pass a list of dictionaries here, they will automatically get UUIDs assigned. See the `Document` class for details) :param documents: a list of Python dictionaries or a list of Haystack Document objects. For documents as dictionaries, the format is {"content": ""}. Optionally: Include meta data via {"content": "", "meta":{"name": ", "author": "somebody", ...}} It can be used for filtering and is accessible in the responses of the Finder. Advanced: If you are using your own Elasticsearch mapping, the key names in the dictionary should be changed to what you have set for self.content_field and self.name_field. :param index: Elasticsearch index where the documents should be indexed. If not supplied, self.index will be used. :param batch_size: Number of documents that are passed to Elasticsearch's bulk function at a time. :param duplicate_documents: Handle duplicates document based on parameter options. Parameter options : ( 'skip','overwrite','fail') skip: Ignore the duplicates documents overwrite: Update any existing documents with the same ID when adding documents. fail: an error is raised if the document ID of the document being added already exists. :raises DuplicateDocumentError: Exception trigger on duplicate document :return: None """ tree_code = r""" class Tree: def __init__(self): self.val = None self.left = None self.right = None """ insert_code = r""" def insert(self, val): if self.val: if val < self.val: if self.left is None: self.left = Tree(val) else: self.left.insert(val) elif val > self.val: if self.right is None: self.right = Tree(val) else: self.right.insert(val) else: self.val = val """ display_code = r""" def display_tree(self: Tree, prefix='value: '): current_node = self.val if self.left: self.left.display_tree() print(prefix, current_node) if self.right: self.right.display_tree() """ article_string = r"""CodeXGLLUE task definition (and dataset): **Code summarization (CodeSearchNet)**: _A model is given the task to generate natural language comments for a programming language code input._ For further details, see the [CodeXGLUE](https://github.com/microsoft/CodeXGLUE) benchmark dataset and open challenge for code intelligence. """ descr_string = 'The application takes as input the python code for a function, or a class, and generates a documentation string, or code comment, for it using codeT5 fine tuned for code2text generation. Code to text generation, or code summarization, is a CodeXGLUE generation, or sequence to sequence, downstream task. CodeXGLUE stands for General Language Understanding Evaluation benchmark *for code*, which includes diversified code intelligence downstream inference tasks and datasets.' def pygen_func(nl_code_intent): pass # TODO: generate code PL from intent NL + search in corpus # inputs = {'code_nl': code_nl} # payload = json.dumps(inputs) # prediction = req.request(CT5_METHOD, CT5_URL, data=payload) # prediction = req.request(CT5_METHOD, CT5_URL, json=req_data) # answer = json.loads(prediction.content.decode("utf-8")) # return str(answer) # CT5_URL = "https://api-inference.huggingface.co/models/nielsr/codet5-small-code-summarization-ruby"