Update README.md

README.md

@@ -18,20 +18,13 @@ It is a state-of-the-art language model for MPNet for Covid-19 dataset with focu
 !git lfs install
 
 !git clone https://huggingface.co/shaina/CoQUAD_MPNet
-# if you want to clone without large files – just their pointers
-# prepend your git clone with the following env var:
 GIT_LFS_SKIP_SMUDGE=1
 
-
- 
-
 from haystack.utils import clean_wiki_text, convert_files_to_dicts, fetch_archive_from_http, print_answers
 from haystack.nodes import FARMReader, TransformersReader
-# Recommended: Start Elasticsearch using Docker via the Haystack utility function
 from haystack.utils import launch_es
 
 launch_es()
-# In Colab / No Docker environments: Start Elasticsearch from source
 ! wget https://artifacts.elastic.co/downloads/elasticsearch/elasticsearch-7.9.2-linux-x86_64.tar.gz -q
 ! tar -xzf elasticsearch-7.9.2-linux-x86_64.tar.gz
 ! chown -R daemon:daemon elasticsearch-7.9.2
@@ -42,9 +35,7 @@ es_server = Popen(['elasticsearch-7.9.2/bin/elasticsearch'],
                    stdout=PIPE, stderr=STDOUT,
                    preexec_fn=lambda: os.setuid(1)  # as daemon
                   )
-# wait until ES has started
 ! sleep 30
-# Connect to Elasticsearch
 
 from haystack.document_stores import ElasticsearchDocumentStore
 document_store = ElasticsearchDocumentStore(host="localhost", username="", password="", index="document")
@@ -62,7 +53,6 @@ from haystack import Document
 from haystack.document_stores import FAISSDocumentStore
 from haystack.nodes import RAGenerator, DensePassageRetriever
 
-# Use data to initialize Document objects
 titles = list(df["document_identifier"].values)
 texts = list(df["document_text"].values)
 documents: List[Document] = []
@@ -75,11 +65,6 @@ for title, text in zip(titles, texts):
             }
         )
     )
-
-
-
-
-# Now, let's write the dicts containing documents to our DB.
 document_store.write_documents(documents)
 
 from haystack.nodes import ElasticsearchRetriever
@@ -88,15 +73,9 @@ reader = FARMReader(model_name_or_path="/content/drive/MyDrive/CoQUAD_MPNet", us
 
 from haystack.pipelines import ExtractiveQAPipeline
 pipe = ExtractiveQAPipeline(reader, retriever)
-# You can configure how many candidates the reader and retriever shall return
-# The higher top_k_retriever, the better (but also the slower) your answers. 
-
-
 prediction = pipe.run(
     query="What is post-COVID?", params={"Retriever": {"top_k": 10}, "Reader": {"top_k": 5}}
 )
-
-# Now you can either print the object directly...
 from pprint import pprint
 
 pprint(prediction)