First version

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.pdf filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,27 @@
+# Application file for Gradio App
+
+import gradio as gr
+import time
+from hay.pipeline import rs_pipeline
+
+with gr.Blocks() as chat:
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox()
+    clear = gr.ClearButton([msg, chatbot])
+
+    def user(user_message, history):
+        return "", history + [[user_message, None]]
+
+    def respond(message, chat_history):
+        question = str(message)
+        answer = rs_pipeline(question)
+        bot_message = answer
+        chat_history.append((message, bot_message))
+        time.sleep(2)
+        return " ", chat_history
+    
+    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+
+def application():
+    chat.launch()
+

clear.py

@@ -0,0 +1,8 @@
+# USE THIS FILE TO CLEAR GPU CACHE
+
+import gc
+import torch
+# def report_gpu():
+print(torch.cuda.list_gpu_processes())
+gc.collect()
+torch.cuda.empty_cache()

data/Bandeira etal2019 - TRD - EV last mile Rio de Janeiro.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d1b1d2ab290adee450d72ce4d36681c7a823c5d15efd61468be44f6a6b6f5a3
+size 1080580

data/Bayer_Aklin2020 - ES - EU ETS reduced CO2.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c34e0b4ce49fd511f441e9e41fa00b6ffb781372b453170a846aaf647a5371c
+size 684692

data/Belavina2020 - MSOM - appendix.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2875ff00ce0f04c01018971ce296e68b45a107befeec34c2409f11af84a1b7c6
+size 1271531

data/Belavina2020 - MSOM - grocery store density and food waste.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a85c9d89c27d4220fbac0c139a6c2a6c8fe43e6f74cf47648b69b04b0d476e30
+size 1029737

data/Beloavia etal2017 - MS - online grocery retail - online appendix.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d51453559bfd9ff58520cc93e9bce4e25883fca9fb8a9434f3e2e6351ebcb930
+size 1195260

data/Beloavia etal2017 - MS - online grocery retail.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8eba61b54c22cbb2aa5a2a55cb3d903eccb3ae2fe2f13aec6d0234c1cab0a31
+size 518288

data/Cachon 2014 - MS - Retail Store Density and the Cost of Greenhouse Gas Emissions.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b662a5533e51cfc2bfac81d41961b1bba4ffad4443386ed35dbd92da131e4d64
+size 400283

data/Carlsson etal2016 - OR - household-level economics of scale.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d160fd7121de0f203c520286599c28814077029a3e0d471c927b68a8183d133
+size 551476

data/Carlsson_Jia2014 - TS - continuous facility location -sm.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e9124240851e4698c9c01e273b82f98624e9e4dd917f18aac673fada90afce7
+size 432199

data/Carlsson_Jia2014 - TS - continuous facility location.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57acd403a3b56be6f828f1ed05bcc264960d131c5fb2192a78d95e77c3b95781
+size 1692461

data/Chakraborty etal2021 - JORS - EV adoption and policy decision.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0eacf24de220b0708cbdb8781997a7eb20eb1ba2df3221ca5395e82f1ee5592
+size 2798560

data/Dilek etal2017 - EJOR - retail location carbon penalty.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75edc2505d908e6824b5031149100158330f2727fa734725f559dd628a8333d3
+size 1326566

data/Edwards etal2009 - IJPDLM - carbon footprints of conventional and online retailing.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61bb1ca9b33a288d4ea680559199d9ec529f75f0956d2f70efd8aa01f1f3d92d
+size 237714

data/Fan etal2022 - MS - price commitment control carbon emissions.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c36295c19a33c3e510ee80da493acf6da9da48b6e7d0fdcf8203368d1a67f4dc
+size 1531063

data/Figliozzi2020 - TRD - emission reduction autonomous vehicles.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f38845c42403de50285545b64d7860fd675ca9433cd0ef90fb4494973329432e
+size 678602

data/GLS2020 - sustainability report.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde30d8d1e45adcf5cd530c5164abb30beae8825a59663aa22e821f97260a54a
+size 5286679

data/Gao etal2018 - TRE - green supply chain consumer.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32a9d9451fde6c2d2ba25694f889734c80e4c1b0ffafa6beb18a697899272d82
+size 1034859

data/Giesler_Veresiu2014 - JCR - responsible consumer.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1473f5f29cbc719745bec983dfb7adefcd15d45a37f207fc2c3fe41dba79f71b
+size 426868

data/Gong_Zhou2013 - OR - production plan with emissions trading.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:934962c1ecb3250229dfd51f99919219d3222c64c040bdee9dc3e674ee40168a
+size 387375

data/Goodchild_Toy2018 - TRD - drone.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc5abcd978e565a28dc55130830a9ab70ce9338b799682f00a144628dd6d7a8c
+size 2325404

data/Hong_Zimmerman2021 - TRD - GHG autonomous vehicles.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6153c7d355b54546b7d5851671745fcea2732d9684f055cb3fb227971a34e8f
+size 1455529

data/Jaller_Pahwa2020 - TRD - environmental impact of online shopping.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a9b4557084e62b0fa2fd25ec1f45b5ce4642a1a0cfe9f5ab14af68b3aa24947
+size 1780179

data/Kopplin etal2021- TRD - consumer acceptance of shared e-scooters.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5539f86cf02f250119af34c0fc4bdff1c144458b82e04c1266f6f38e0e9618fa
+size 798226

data/McKinnon2022 - Environmentally sustainable city logistics.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd02c40f124beef047acf208aca769a58513e6b1b75de0e3071ed58836022dc7
+size 992619

data/McLeod etal2020 - TRD - porters and cycle couriers for last mile delivery.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac3f78a064fd764955d18380d48cdb64e6d158d65baf26facbb7972033deda2b
+size 2125351

data/Park etal2015 - POM - SC design monopolistic competition.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3595af774cc1925517ecc1413a8fe66f8731bab82857c211bda432c488afc875
+size 894201

data/Perotti etal2021 - BSE - logistics sites CO2eq.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eba42c20a6aaf57d70f389f36bc846441ebb13c77ce7f7912ef302a75a2fc4f
+size 2122111

data/Qi etal2018 - MSOM - shared mobility for last-mile delivery.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cea1eefeaf4c2453c2a69c43e4872d853ad677a5edcd3363f2da6d5aaa4b9b1b
+size 1866416

data/Shahmohammadi etal2020 - EST - carbon footprint online retailing.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9df7e46465abee74f54918fd8f426beebaf04042e516662c00540f7e973ae2b
+size 1554492

data/Song etal2020 - POM - value of buy-online-and-pickup-in-store.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf76bfb9c860407186b627eec631ec0e4536cbbb9392e9065976647a4e4b017
+size 316808

data/Tezer_Bodur2020 - JCR - greenconsumption effect.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36ab9ce0a583cdc016703c7283accb075c0de4d7913ccd54b315683f271a55f8
+size 322643

data/UPS2019 - sustainability progress report.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34e06fb69b4d51f08e34afcf602dc8075fd08ae2e4dfc74c5aa67072892e42e1
+size 5345260

data/Yuan etal2018 - POM - control of emissions trading and production.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6fada733543daad99890048255983fc0d874caf802250af18147409834fd19d
+size 807730

data/vanLoon etal2015 - JCP - emissions from online retailing.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:288364c2562ff08ed3f440893b1c6fa89730a6f4207f564887776478bdfbeb93
+size 2037787

hay/model.py

@@ -0,0 +1,36 @@
+from haystack.nodes import PromptNode, PromptTemplate
+from haystack.nodes import AnswerParser
+from haystack.nodes import TransformersSummarizer
+from haystack import Document
+
+
+
+
+def prompting_model():
+    '''
+    Define a prompt node in haystack pipeline
+    ''' 
+
+    prompt_node = PromptNode(model_name_or_path="facebook/galactica-125m", default_prompt_template="deepset/question-answering-per-document")
+    
+    # prompt_node = PromptNode(model_name_or_path="facebook/opt-350m", default_prompt_template=lfqa_prompt)
+
+    return prompt_node
+
+
+def summarize():
+
+    '''
+    Use a summarizer node, to summarize the output of generator
+    To remove redundancy/repitition
+    '''
+
+    summarizer = TransformersSummarizer(model_name_or_path="google/pegasus-xsum")
+
+    return summarizer
+
+
+
+
+
+    

hay/pipeline.py

@@ -0,0 +1,50 @@
+from hay.model import prompting_model, summarize
+from haystack.pipelines import Pipeline, SearchSummarizationPipeline
+from hay.retriever import retriever1
+
+def rg_pipeline(question):
+    '''
+    Defines a pipeline of retriever and generator and generates output for the given question
+    '''
+
+    prompt_node = prompting_model() 
+    retriever = retriever1()
+
+    pipe = Pipeline()
+    pipe.add_node(component=retriever, name="retriever", inputs=["Query"])
+    pipe.add_node(component=prompt_node, name="prompt_node", inputs=["retriever"])
+
+    output = pipe.run(query=question)
+
+    for i in range(1, len(output['results'])):
+        print("Value at  " + str(i))
+        print(output["results"][i])
+
+    return None
+
+
+def rs_pipeline(question):
+    '''
+    Defines a pipeline of retriever and summarizer and generates output for the given question
+    '''
+
+    retriever = retriever1()
+    summarizer = summarize()
+
+    # Get top 10 results from the retriever and summarize them
+    pipeline = SearchSummarizationPipeline(summarizer=summarizer, retriever=retriever)
+    result = pipeline.run(query=question, params={"Retriever": {"top_k": 5}})
+
+    output = ''
+    for i in range(len(result['documents'])):
+        output += result['documents'][i].meta['summary']
+
+    # print(output)
+    
+    return output
+
+
+
+
+
+

hay/retriever.py

@@ -0,0 +1,76 @@
+from haystack.utils import convert_files_to_docs
+from haystack.nodes import PreProcessor
+
+import pyarrow as pa
+import pyarrow.dataset as ds
+import pandas as pd
+from datasets import Dataset, load_from_disk
+import pandas as pd
+
+from haystack.nodes import BM25Retriever
+from haystack.document_stores import InMemoryDocumentStore
+from haystack.document_stores import FAISSDocumentStore
+from haystack.nodes import DensePassageRetriever
+from haystack.document_stores import InMemoryDocumentStore
+from haystack.nodes import TfidfRetriever
+
+
+import warnings
+warnings.filterwarnings('ignore')
+
+def generate_docs(overlap, length):
+
+    '''
+    Takes in split length and split overlap
+    Saves the docs in a pandas dataframe
+    '''
+    all_docs = convert_files_to_docs(dir_path='data')
+
+    preprocessor = PreProcessor(
+        clean_empty_lines=True,
+        clean_whitespace=True,
+        clean_header_footer=True,
+        split_by="word",
+        split_overlap=overlap,
+        split_length=length,
+        split_respect_sentence_boundary=False,
+    )
+
+    docs = preprocessor.process(all_docs)
+
+    # print(f"n_files_input: {len(all_docs)}\nn_docs_output: {len(docs)}")
+
+    df = pd.DataFrame(docs)
+    dataset = Dataset(pa.Table.from_pandas(df))
+    dataset.save_to_disk('outputs/docs-dataset')
+
+    return None
+
+
+def retriever1():
+    '''
+    Use BM25 Retriever to retrieve data
+    '''
+
+    dataset = load_from_disk('outputs/docs-dataset')
+
+    # BM25Retriever with InMemoryDocumentStore
+    document_store = InMemoryDocumentStore(use_bm25=True)
+    document_store.write_documents(dataset)
+    retriever = BM25Retriever(document_store=document_store, top_k=5)
+
+    return retriever
+
+
+# def retriever2():
+#     document_store = FAISSDocumentStore(similarity="dot_product")
+#     retriever = DensePassageRetriever(
+#         document_store=document_store,
+#         query_embedding_model="facebook/dpr-question_encoder-single-nq-base",
+#         passage_embedding_model="facebook/dpr-ctx_encoder-single-nq-base"
+#     )
+#     document_store.update_embeddings(retriever)
+
+#     return retriever
+# generate_docs(20, 250)
+# ret = retriever2()

main.py

@@ -0,0 +1,64 @@
+import argparse
+from hay.retriever import generate_docs
+from hay.pipeline import rg_pipeline, rs_pipeline
+from app import application
+
+
+def main():
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument(
+        '--docs', dest='docs',
+        action = 'store_true'
+    )
+
+    parser.add_argument(
+        '--rgpipeline', dest='rgpipeline',
+        action = 'store_true'
+    )
+
+    parser.add_argument(
+        '--rspipeline', dest='rspipeline',
+        action='store_true'
+    )
+
+    parser.add_argument(
+        '--gradio', dest='gradio',
+        action='store_true'
+    )
+
+    args = parser.parse_args()
+
+    if args.docs:
+        '''
+        Use this argument to generate the docs and store in DOCUMENT format
+        '''
+        generate_docs(overlap=10, length=100)
+
+    if args.rgpipeline:
+        '''
+        Use this argument to run the base retriever generator pipeline
+        '''
+        question = "How to reduce emissions?"
+        rg_pipeline(question)
+
+    if args.rspipeline:
+        '''
+        Use this argument to run the retriever summarizer pipeline
+        '''
+
+        question = "How to reduce emissions in last mile supply chain?"
+        answer = rs_pipeline(question)     
+        print(answer)
+
+    if args.gradio:
+        '''
+        Use this argument to run the application
+        '''   
+        application()
+
+    return None
+
+
+if __name__ == '__main__':
+    main()

outputs/docs-dataset/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d321d150f9b0febdc19c3874580ec5e6907ce98edcb356f088907d2b6bf5f655
+size 4072512

outputs/docs-dataset/dataset_info.json

@@ -0,0 +1,60 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "id": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "content": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "content_type": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "meta": {
+      "_split_id": {
+        "dtype": "int64",
+        "_type": "Value"
+      },
+      "_split_overlap": [
+        {
+          "doc_id": {
+            "dtype": "string",
+            "_type": "Value"
+          },
+          "range": {
+            "feature": {
+              "dtype": "int64",
+              "_type": "Value"
+            },
+            "_type": "Sequence"
+          }
+        }
+      ],
+      "name": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "id_hash_keys": {
+      "feature": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    },
+    "score": {
+      "dtype": "null",
+      "_type": "Value"
+    },
+    "embedding": {
+      "dtype": "null",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

outputs/docs-dataset/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "b673ed2843344a0a",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

outputs/faiss_index.json

@@ -0,0 +1 @@
+{"faiss_index_factory_str": "Flat"}