Update README.md

README.md

@@ -1,12 +1,111 @@
 ---
-language: 
-  - en
-
-tags:
-- COVID-19
-- MPNet
-license: "MIT"
+language: en
+license: mit
 datasets:
-- https://huggingface.co/datasets/shaina/covid19
+- covid19
+---
+
+# CoQUAD_MPNet : MPNet model for COVID-19
+
+## Introduction
+
+It is a state-of-the-art language model for MPNet for Covid-19 dataset with focus on post-covid.
+## How to use for Deepset Haystack
+
+%cd /content/drive/MyDrive
+!sudo apt-get install git-lfs
+
+!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
+
+import os
+from subprocess import Popen, PIPE, STDOUT
+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")
+
+import pandas as pd
+df=pd.read_excel('/content/covid.xlsx')
+df.fillna(value="", inplace=True)
+
+print(df.head())
+
+from typing import List
+import requests
+import pandas as pd
+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] = []
+for title, text in zip(titles, texts):
+    documents.append(
+        Document(
+            content=text,
+            meta={
+                "name": title or ""
+            }
+        )
+    )
+
+
+
+
+# Now, let's write the dicts containing documents to our DB.
+document_store.write_documents(documents)
+
+from haystack.nodes import ElasticsearchRetriever
+retriever = ElasticsearchRetriever(document_store=document_store)
+reader = FARMReader(model_name_or_path="/content/drive/MyDrive/CoQUAD_MPNet", use_gpu=True)
+
+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)
+
+
+
+## Authors 
+
+Shaina Raza
+
 
----
+```