deepset-ai · ZanSara · Oct 28, 2021 · Oct 28, 2021 · Oct 28, 2021 · Oct 28, 2021
diff --git a/docs/_src/tutorials/tutorials/1.md b/docs/_src/tutorials/tutorials/1.md
@@ -237,9 +237,58 @@ prediction = pipe.run(
 
 
 ```python
+# Change `minimal` to `medium` or `all` to see a more detailed output
 print_answers(prediction, details="minimal")
 ```
 
+
+```python
+# Alternative: print the object
+
+# print(predictions)
+
+# or:
+
+# import json
+# print(json.dumps(prediction, indent=4, default=str))
+
+# Sample output:
+# {
+#     "query": "Who is the father of Arya Stark?",
+#     "no_ans_gap": 11.688868522644043,
+#     "answers": [
+#         "Answer(answer: 'Eddard', score: 0.9919578731060028, context: 's Nymeria after a legendary warrior queen. She travels with her father, Eddard, to King's Landing wh...')",
+#         "Answer(answer: 'Ned', score: 0.9767240881919861, context: '\n====Season 1====\nArya accompanies her father Ned and her sister Sansa to King's Landing. Before the...')",
+#         "Answer(answer: 'Lord Eddard Stark', score: 0.8930400013923645, context: 'ark daughters.\nDuring the Tourney of the Hand to honour her father Lord Eddard Stark, Sansa Stark is...')",
+#         "Answer(answer: 'Joffrey', score: 0.6753827035427094, context: 'laying with one of his wooden toys.\nAfter Eddard discovers the truth of Joffrey's paternity, he tell...')",
+#         "Answer(answer: 'Robb', score: 0.6665983200073242, context: 'allow the army to cross the river and to commit his troops in return for Robb and Arya Stark marryin...')"
+#     ],
+#     "documents": [
+#         "Document(id: 6b181174d1237878b706e6a12d69e92, content: '\n===In the Riverlands===\nThe Stark army reaches the Twins, a bridge stronghold controlled by Walder  ...')",
+#         "Document(id: a4d2cc51d351b785c6effddd3345bb39, content: '\n===On the Kingsroad===\nCity Watchmen search the caravan for Gendry but are turned away by Yoren. Ge ...')",
+#         "Document(id: d1f36ec7170e4c46cde65787fe125dfe, content: '\n===''A Game of Thrones''===\nSansa Stark begins the novel by being betrothed to Crown Prince Joffrey ...')",
+#         "Document(id: dd4e070a22896afa81748d6510006d2, content: '\n===Season 2===\nGendry travels North with Yoren and other Night's Watch recruits, including Arya Sta ...')",
+#         "Document(id: 956aa2b653c6debcb6cb217531a6be58, content: '\n===In King's Landing===\nAfter Varys tells him that Sansa Stark's life is also at stake, Eddard \"Ned ...')",
+#         "Document(id: 180c2a6b36369712b361a80842e79356, content: '\n====Season 1====\nArya accompanies her father Ned and her sister Sansa to King's Landing. Before the ...')",
+#         "Document(id: fc56eb160221cbdc74d223383680dbeb, content: '\n==== ''A Storm of Swords'' and ''A Feast for Crows'' ====\nPrior to the Red Wedding, Roose Bolton pr ...')",
+#         "Document(id: e60cb63e43a5a01694aea3a5cab14281, content: '\n===House Frey===\n* '''Walder Frey''' (seasons 1, 3, 6\u20137) portrayed by David Bradley. David Bradley  ...')",
+#         "Document(id: ba2a8e87ddd95e380bec55983ee7d55f, content: '\n==== ''A Game of Thrones'' ====\nArya adopts a direwolf cub, which she names Nymeria after a legenda ...')",
+#         "Document(id: 212af6309da6cb02c3c0e1da9f6fdf71, content: '\n== Character description ==\nGendry was conceived and born in King's Landing after Robert's Rebellio ...')"
+#     ],
+#     "root_node": "Query",
+#     "params": {
+#         "Retriever": {
+#             "top_k": 10
+#         },
+#         "Reader": {
+#             "top_k": 5
+#         }
+#     },
+#     "node_id": "Reader"
+# }
+
+```
+
 ## About us
 
 This [Haystack](https://github.com/deepset-ai/haystack/) notebook was made with love by [deepset](https://deepset.ai/) in Berlin, Germany

diff --git a/docs/_src/tutorials/tutorials/11.md b/docs/_src/tutorials/tutorials/11.md
@@ -296,7 +296,7 @@ Below, we define a very naive `QueryClassifier` and show how to use it:
 
 
 ```python
-class QueryClassifier(BaseComponent):
+class MyQueryClassifier(BaseComponent):
     outgoing_edges = 2
 
     def run(self, query: str):
@@ -307,7 +307,7 @@ class QueryClassifier(BaseComponent):
 
 # Here we build the pipeline
 p_classifier = Pipeline()
-p_classifier.add_node(component=QueryClassifier(), name="QueryClassifier", inputs=["Query"])
+p_classifier.add_node(component=MyQueryClassifier(), name="QueryClassifier", inputs=["Query"])
 p_classifier.add_node(component=es_retriever, name="ESRetriever", inputs=["QueryClassifier.output_1"])
 p_classifier.add_node(component=dpr_retriever, name="DPRRetriever", inputs=["QueryClassifier.output_2"])
 p_classifier.add_node(component=reader, name="QAReader", inputs=["ESRetriever", "DPRRetriever"])
@@ -316,12 +316,12 @@ p_classifier.draw("pipeline_classifier.png")
 # Run only the dense retriever on the full sentence query
 res_1 = p_classifier.run(query="Who is the father of Arya Stark?")
 print("DPR Results" + "\n" + "="*15)
-print_answers(res_1)
+print_answers(res_1, details="minimal")
 
 # Run only the sparse retriever on a keyword based query
 res_2 = p_classifier.run(query="Arya Stark father")
 print("ES Results" + "\n" + "="*15)
-print_answers(res_2)
+print_answers(res_2, details="minimal")
 ```
 
 ## Evaluation Nodes

diff --git a/docs/_src/tutorials/tutorials/13.md b/docs/_src/tutorials/tutorials/13.md
@@ -98,9 +98,15 @@ which the the document can answer.
 
 ```python
 question_generation_pipeline = QuestionGenerationPipeline(question_generator)
-for document in document_store:
-        result = question_generation_pipeline.run(documents=[document])
-        pprint(result)
+for idx, document in enumerate(document_store):
+
+    print(f"\n * Generating questions for document {idx}: {document.content[:50]}...")
+    result = question_generation_pipeline.run(documents=[document])
+
+    print("Generated questions:")
+    for result in result["generated_questions"]:
+        for question in result["questions"]:
+            print(f" - {question}")
 ```
 
 ## Retriever Question Generation Pipeline
@@ -111,8 +117,14 @@ This pipeline takes a query as input. It retrieves relevant documents and then g
 ```python
 retriever = ElasticsearchRetriever(document_store=document_store)
 rqg_pipeline = RetrieverQuestionGenerationPipeline(retriever, question_generator)
+
+print(f"\n * Generating questions for documents matching the query 'Arya Stark'")
 result = rqg_pipeline.run(query="Arya Stark")
-pprint(result)
+
+print("Generated questions:")
+for result in result["generated_questions"]:
+    for question in result["questions"]:
+        print(f" - {question}")
 ```
 
 ## Question Answer Generation Pipeline
@@ -124,9 +136,15 @@ a Reader model
 ```python
 reader = FARMReader("deepset/roberta-base-squad2")
 qag_pipeline = QuestionAnswerGenerationPipeline(question_generator, reader)
-for document in tqdm(document_store):
+for idx, document in enumerate(tqdm(document_store)):
+
+    print(f"\n * Generating questions and answers for document {idx}: {document.content[:20]}...")
     result = qag_pipeline.run(documents=[document])
-    pprint(result)
+
+    for pair in result["results"]:
+        print(f" - Q:{pair['query']}")
+        for answer in pair["answers"]:
+            print(f"      A: {answer.answer}")
 ```
 
 ## About us

diff --git a/haystack/schema.py b/haystack/schema.py
@@ -186,10 +186,10 @@ def __eq__(self, other):
                 getattr(other, 'id_hash_keys', None) == self.id_hash_keys)
 
     def __repr__(self):
-        return str(self.to_dict())
+        return f"<Document: {str(self.to_dict())}>"
 
     def __str__(self):
-        return f"content: {self.content[:100]} {'[...]' if len(self.content) > 100 else ''}"
+        return f"<Document: id={self.id}, content='{self.content[:100]} {'...' if len(self.content) > 100 else ''}'>"
 
     def __lt__(self, other):
         """ Enable sorting of Documents by score """
@@ -262,10 +262,10 @@ def __lt__(self, other):
         return self.score < other.score
 
     def __str__(self):
-        return f"answer: {self.answer} \nscore: {self.score} \ncontext: {self.context}"
+        return f"<Answer: answer='{self.answer}', score={self.score}, context='{self.context[:50]}{'...' if len(self.context) > 50 else ''}'>"
 
     def to_dict(self):
-        return asdict(self)
+        return f"<Answer {asdict(self)}>"
 
     @classmethod
     def from_dict(cls, dict:dict):

diff --git a/haystack/utils/export_utils.py b/haystack/utils/export_utils.py
@@ -21,7 +21,7 @@ def print_answers(results: dict, details: str = "all"):
     """
     Utilitiy function to print results of Haystack pipelines
     :param results: Results from a pipeline
-    :param details: One of ["minimum", "medium", "all]. Defining the level of details to print.
+    :param details: One of ["minimum", "medium", "all"]. Defining the level of details to print.
     :return: None
     """
     # TODO: unify the output format of Generator and Reader so that this function doesn't have the try/except
@@ -47,6 +47,8 @@ def print_answers(results: dict, details: str = "all"):
     except:
         if details == "minimal":
             print(f"Query: {results['query']}")
+            if not "answers" in results.keys():
+                print("No answers!")
             for a in results["answers"]:
                 print(f"Answer: {a['answer']}")
         else:

diff --git a/tutorials/Tutorial10_Knowledge_Graph.py b/tutorials/Tutorial10_Knowledge_Graph.py
@@ -2,6 +2,7 @@
 import subprocess
 import time
 from pathlib import Path
+from pprint import pprint
 
 from haystack.nodes import Text2SparqlRetriever
 from haystack.document_stores import GraphDBKnowledgeGraph
@@ -26,7 +27,7 @@ def tutorial10_knowledge_graph():
 
     # Start a GraphDB server
     if LAUNCH_GRAPHDB:
-        logging.info("Starting GraphDB ...")
+        print("Starting GraphDB ...\n")
         status = subprocess.run(
             ['docker run -d -p 7200:7200 --name graphdb-instance-tutorial docker-registry.ontotext.com/graphdb-free:9.4.1-adoptopenjdk11'], shell=True
         )
@@ -52,8 +53,13 @@ def tutorial10_knowledge_graph():
 
     # Import triples of subject, predicate, and object statements from a ttl file
     kg.import_from_ttl_file(index="tutorial_10_index", path=Path(graph_dir+"triples.ttl"))
-    logging.info(f"The last triple stored in the knowledge graph is: {kg.get_all_triples()[-1]}")
-    logging.info(f"There are {len(kg.get_all_triples())} triples stored in the knowledge graph.")
+
+    print()
+    print("# KNOWLEDGE GRAPH CONTENT")
+    print("#########################")
+    print(f"There are {len(kg.get_all_triples())} triples stored in the knowledge graph.")
+    print(f"The last triple stored in the knowledge graph is:\n{kg.get_all_triples()[-1]}")
+    print()
 
     # Define prefixes for names of resources so that we can use shorter resource names in queries
     prefixes = """PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
@@ -69,25 +75,30 @@ def tutorial10_knowledge_graph():
     # One limitation though: our pre-trained model can only generate questions about resources it has seen during training.
     # Otherwise, it cannot translate the name of the resource to the identifier used in the knowledge graph.
     # E.g. "Harry" -> "hp:Harry_potter"
-
     query = "In which house is Harry Potter?"
-    logging.info(f"Translating the text query \"{query}\" to a SPARQL query and executing it on the knowledge graph...")
+    print(f"\nTranslating the text query \"{query}\" to a SPARQL query and executing it on the knowledge graph...")
+    print("   -> Correct SPARQL query: select ?a { hp:Harry_potter hp:house ?a . }")
+    print("   -> Correct answer: Gryffindor")
     result = kgqa_retriever.retrieve(query=query)
-    logging.info(result)
-    # Correct SPARQL query: select ?a { hp:Harry_potter hp:house ?a . }
-    # Correct answer: Gryffindor
+    print("Results: ")
+    for r in result:
+        pprint(r)
 
-    logging.info("Executing a SPARQL query with prefixed names of resources...")
+    print("\nExecuting a SPARQL query with prefixed names of resources...")
+    print("   -> Paraphrased question: Who is the keeper of keys and grounds?")
+    print("   -> Correct answer: Rubeus Hagrid")
     result = kgqa_retriever._query_kg(sparql_query="select distinct ?sbj where { ?sbj hp:job hp:Keeper_of_keys_and_grounds . }")
-    logging.info(result)
-    # Paraphrased question: Who is the keeper of keys and grounds?
-    # Correct answer: Rubeus Hagrid
+    print(" * Results: ")
+    for r in result:
+        pprint(r)
 
-    logging.info("Executing a SPARQL query with full names of resources...")
+    print("\nExecuting a SPARQL query with full names of resources...")
+    print("   -> Paraphrased question: What is the patronus of Hermione?")
+    print("   -> Correct answer: Otter")
     result = kgqa_retriever._query_kg(sparql_query="select distinct ?obj where { <https://deepset.ai/harry_potter/Hermione_granger> <https://deepset.ai/harry_potter/patronus> ?obj . }")
-    logging.info(result)
-    # Paraphrased question: What is the patronus of Hermione?
-    # Correct answer: Otter
+    print("Results: ")
+    for r in result:
+        pprint(r)
 
 
 if __name__ == "__main__":

diff --git a/tutorials/Tutorial11_Pipelines.ipynb b/tutorials/Tutorial11_Pipelines.ipynb
@@ -547,7 +547,7 @@
    "cell_type": "code",
    "execution_count": null,
    "source": [
-    "class QueryClassifier(BaseComponent):\n",
+    "class MyQueryClassifier(BaseComponent):\n",
     "    outgoing_edges = 2\n",
     "\n",
     "    def run(self, query: str):\n",
@@ -558,7 +558,7 @@
     "\n",
     "# Here we build the pipeline\n",
     "p_classifier = Pipeline()\n",
-    "p_classifier.add_node(component=QueryClassifier(), name=\"QueryClassifier\", inputs=[\"Query\"])\n",
+    "p_classifier.add_node(component=MyQueryClassifier(), name=\"QueryClassifier\", inputs=[\"Query\"])\n",
     "p_classifier.add_node(component=es_retriever, name=\"ESRetriever\", inputs=[\"QueryClassifier.output_1\"])\n",
     "p_classifier.add_node(component=dpr_retriever, name=\"DPRRetriever\", inputs=[\"QueryClassifier.output_2\"])\n",
     "p_classifier.add_node(component=reader, name=\"QAReader\", inputs=[\"ESRetriever\", \"DPRRetriever\"])\n",
@@ -567,12 +567,12 @@
     "# Run only the dense retriever on the full sentence query\n",
     "res_1 = p_classifier.run(query=\"Who is the father of Arya Stark?\")\n",
     "print(\"DPR Results\" + \"\\n\" + \"=\"*15)\n",
-    "print_answers(res_1)\n",
+    "print_answers(res_1, details=\"minimal\")\n",
     "\n",
     "# Run only the sparse retriever on a keyword based query\n",
     "res_2 = p_classifier.run(query=\"Arya Stark father\")\n",
     "print(\"ES Results\" + \"\\n\" + \"=\"*15)\n",
-    "print_answers(res_2)"
+    "print_answers(res_2, details=\"minimal\")"
    ],
    "outputs": [],
    "metadata": {