Updated App

README.md

@@ -1,13 +1,16 @@
 ---
-title: Chat With Pdf
-emoji: 📊
-colorFrom: purple
-colorTo: yellow
+title: chat-with-pdf
+emoji: 😻
+colorFrom: indigo
+colorTo: purple
 sdk: streamlit
-sdk_version: 1.38.0
+sdk_version: 1.33.0
 app_file: app.py
 pinned: false
-license: mit
+header: mini
+license: creativeml-openrail-m
+short_description: pdf scraper RAG
+form: RAG
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,101 @@
+import streamlit as st
+from llama_index.core import StorageContext, load_index_from_storage, VectorStoreIndex, SimpleDirectoryReader, ChatPromptTemplate
+from llama_index.llms.huggingface import HuggingFaceInferenceAPI
+from dotenv import load_dotenv
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+from llama_index.core import Settings
+import os
+import base64
+
+# Load environment variables
+load_dotenv()
+
+# Configure the Llama index settings
+Settings.llm = HuggingFaceInferenceAPI(
+    model_name="google/gemma-1.1-7b-it",
+    tokenizer_name="google/gemma-1.1-7b-it",
+    context_window=3000,
+    token=os.getenv("HF_TOKEN"),
+    max_new_tokens=512,
+    generate_kwargs={"temperature": 0.1},
+)
+Settings.embed_model = HuggingFaceEmbedding(
+    model_name="BAAI/bge-small-en-v1.5"
+)
+
+# Define the directory for persistent storage and data
+PERSIST_DIR = "./db"
+DATA_DIR = "data"
+
+# Ensure data directory exists
+os.makedirs(DATA_DIR, exist_ok=True)
+os.makedirs(PERSIST_DIR, exist_ok=True)
+
+def displayPDF(file):
+    with open(file, "rb") as f:
+        base64_pdf = base64.b64encode(f.read()).decode('utf-8')
+    pdf_display = f'<iframe src="data:application/pdf;base64,{base64_pdf}" width="100%" height="600" type="application/pdf"></iframe>'
+    st.markdown(pdf_display, unsafe_allow_html=True)
+
+def data_ingestion():
+    documents = SimpleDirectoryReader(DATA_DIR).load_data()
+    storage_context = StorageContext.from_defaults()
+    index = VectorStoreIndex.from_documents(documents)
+    index.storage_context.persist(persist_dir=PERSIST_DIR)
+
+def handle_query(query):
+    storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
+    index = load_index_from_storage(storage_context)
+    chat_text_qa_msgs = [
+    (
+        "user",
+        """You are a Q&A assistant named CHATTO, created by Rishi. You have a specific response programmed for when users specifically ask about your creator, Rishi. The response is: "I was created by Rishi, an enthusiast in Artificial Intelligence. He is dedicated to solving complex problems and delivering innovative solutions. With a strong focus on machine learning, deep learning, Python, generative AI, NLP, and computer vision, Rishi is passionate about pushing the boundaries of AI to explore new possibilities." For all other inquiries, your main goal is to provide answers as accurately as possible, based on the instructions and context you have been given. If a question does not match the provided context or is outside the scope of the document, kindly advise the user to ask questions within the context of the document.
+        Context:
+        {context_str}
+        Question:
+        {query_str}
+        """
+    )
+    ]
+    text_qa_template = ChatPromptTemplate.from_messages(chat_text_qa_msgs)
+    
+    query_engine = index.as_query_engine(text_qa_template=text_qa_template)
+    answer = query_engine.query(query)
+    
+    if hasattr(answer, 'response'):
+        return answer.response
+    elif isinstance(answer, dict) and 'response' in answer:
+        return answer['response']
+    else:
+        return "Sorry, I couldn't find an answer."
+
+
+# Streamlit app initialization
+st.title("(PDF) Information and Inference🗞️")
+st.markdown("Retrieval-Augmented Generation") 
+st.markdown("start chat ...🚀")
+
+if 'messages' not in st.session_state:
+    st.session_state.messages = [{'role': 'assistant', "content": 'Hello! Upload a PDF and ask me anything about its content.'}]
+
+with st.sidebar:
+    st.title("Menu:")
+    uploaded_file = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button")
+    if st.button("Submit & Process"):
+        with st.spinner("Processing..."):
+            filepath = "data/saved_pdf.pdf"
+            with open(filepath, "wb") as f:
+                f.write(uploaded_file.getbuffer())
+            # displayPDF(filepath)  # Display the uploaded PDF
+            data_ingestion()  # Process PDF every time new file is uploaded
+            st.success("Done")
+
+user_prompt = st.chat_input("Ask me anything about the content of the PDF:")
+if user_prompt:
+    st.session_state.messages.append({'role': 'user', "content": user_prompt})
+    response = handle_query(user_prompt)
+    st.session_state.messages.append({'role': 'assistant', "content": response})
+
+for message in st.session_state.messages:
+    with st.chat_message(message['role']):
+        st.write(message['content'])

db/default__vector_store.json

@@ -0,0 +1 @@
+{"embedding_dict": {"860863cb-ba90-4287-9ff3-de812a7cf04a": [-0.04935232177376747, 0.014276032336056232, -0.00677516171708703, -0.007499701343476772, 0.0857427641749382, 0.03596746549010277, -0.06747723370790482, 0.035292088985443115, 0.0009802288841456175, 0.011373339220881462, 0.024754010140895844, -0.03062259964644909, 0.011178512126207352, 0.01658494584262371, -0.025193003937602043, 0.007735987193882465, -0.026199763640761375, -0.004099538084119558, 0.03002157434821129, 0.018483860418200493, 0.008464190177619457, -0.03511177375912666, 0.021300099790096283, 0.045198313891887665, 0.02103796787559986, 0.04658903181552887, -0.03597500920295715, -0.07936180382966995, -0.048395734280347824, -0.23985832929611206, 0.05988171696662903, 0.00787472166121006, 0.06542612612247467, 0.016137035563588142, -0.029961371794342995, 0.016481216996908188, -0.020172743126749992, 0.05845439434051514, 0.029444292187690735, 0.0327472984790802, -0.060793109238147736, -0.021447496488690376, -0.010194200091063976, -0.03895203024148941, 0.002724932273849845, -0.04428384453058243, -0.04992429539561272, -0.020091135054826736, -0.008397594094276428, 0.006678513251245022, -0.04897148534655571, -0.060120902955532074, 0.00495715020224452, 0.031236156821250916, -0.024438021704554558, -0.001887921360321343, 0.08040959388017654, 0.0212861318141222, 0.019926222041249275, 0.041057415306568146, 0.0645257979631424, 0.029546035453677177, -0.13904771208763123, 0.01744740828871727, 0.06266944855451584, 0.041324276477098465, -0.0977046936750412, -0.042026087641716, -0.02397708222270012, 0.000938264187425375, -0.031055675819516182, 0.022282985970377922, 0.039871398359537125, 0.011208692565560341, 0.059094201773405075, 0.01761738955974579, 0.03747517243027687, 0.002703616861253977, 0.015252131968736649, -0.0339764729142189, 0.034126173704862595, 0.05502382293343544, 0.020618971437215805, -0.030696270987391472, -0.013595390133559704, -0.02856854349374771, 0.0403427854180336, -0.02784808911383152, -0.004025080241262913, -0.011623065918684006, -0.023647073656320572, -0.021383848041296005, -0.03101491369307041, 0.05079283565282822, -0.04112066701054573, -0.03585713356733322, -0.02295582741498947, 0.0062613822519779205, 0.02795836143195629, 0.45919111371040344, 0.015642572194337845, 0.010819172486662865, -0.018927421420812607, 0.05333065986633301, -0.013381321914494038, -0.06688794493675232, 0.004536801483482122, -0.02615642547607422, -0.024168578907847404, -0.004391009919345379, 0.02736389823257923, 0.02036883682012558, -0.040253669023513794, -0.03790125250816345, 0.007962658070027828, -0.0071958815678954124, 0.049702417105436325, -0.01769251562654972, -0.007585907820612192, -0.012356655672192574, 0.008346965536475182, -0.025942832231521606, 0.030699746683239937, -0.031913790851831436, 0.05911710113286972, -0.05253056809306145, 0.03923376277089119, 0.08774489164352417, 0.038656190037727356, -0.001138997613452375, 0.027105676010251045, 0.027531057596206665, -0.08285865932703018, 0.01835499331355095, -0.00720310490578413, -0.030862700194120407, -0.0021355219651013613, -0.016528071835637093, 0.007597050163894892, 0.02883450873196125, -0.011319754645228386, 0.03828631341457367, -0.007711352314800024, -0.09212921559810638, -0.12980586290359497, 0.153176948428154, 0.011540068313479424, 0.03229355439543724, -0.036570385098457336, -0.05308893322944641, 0.04680844396352768, 0.07722964882850647, -0.019974086433649063, 0.01124553382396698, 0.03856383636593819, 0.031176432967185974, -0.019309746101498604, -0.023881902918219566, -0.020723534747958183, 0.03380262106657028, -0.018595557659864426, -0.030544748529791832, 0.021867908537387848, 0.10692565888166428, 0.01082476507872343, -0.032912179827690125, -0.007422571070492268, 0.044559549540281296, -0.02630840614438057, 0.006297847256064415, -0.005424784496426582, -0.043432921171188354, 0.018201762810349464, 0.016728423535823822, -0.03545304760336876, 0.036799076944589615, -0.00962867308408022, -0.01837957464158535, -0.005215011071413755, 0.006207386497408152, -0.003111738944426179, -0.014922741800546646, -0.07831963896751404, 0.011641087010502815, 0.03601595386862755, 0.01461033709347248, -0.018093876540660858, -0.01139074470847845, 0.004400675185024738, 0.06439895927906036, 0.043229930102825165, -0.05553846061229706, -0.007091710343956947, 0.03263641893863678, -0.01781558059155941, 0.010551278479397297, -0.010003015398979187, -0.005920502822846174, -0.0057300967164337635, -0.06755722314119339, 0.03704983368515968, 0.0756269097328186, 0.03213987126946449, 0.0392606295645237, -0.02188468724489212, 0.005344125907868147, -0.007023293059319258, 0.006461248733103275, 0.05830821394920349, 0.02524745464324951, -0.06875360757112503, 0.0077574849128723145, -0.008623662404716015, 0.017420368269085884, -0.014371651224792004, 0.01098068617284298, 0.015060738660395145, 0.0575602725148201, -0.015285676345229149, 0.055246952921152115, -0.0046562557108700275, -0.0018068264471367002, -0.017236808314919472, -0.3138227164745331, -0.03679979592561722, 0.025411024689674377, 0.04189690202474594, -0.01532608363777399, -0.0593300499022007, 0.007799589075148106, 0.017681816592812538, 0.004527967423200607, 0.014501117169857025, 0.03831024095416069, 0.0643090233206749, -0.06463051587343216, -0.06307888776063919, -0.018941743299365044, -0.014238502830266953, 0.007583525497466326, -0.017396165058016777, -0.032528795301914215, 0.04459691792726517, 0.016582539305090904, 0.002379573881626129, -0.0007301989244297147, -0.01501720491796732, 0.07269556820392609, -0.03588758409023285, 0.1032787337899208, -0.06350622326135635, 0.006171433720737696, 0.015278211794793606, -0.02456526644527912, 0.03500528261065483, -0.03471928462386131, -0.03898708149790764, 0.023004775866866112, -0.028884489089250565, -0.057739198207855225, -0.0035506936255842447, -0.019762180745601654, -0.039818767458200455, -0.020245185121893883, -0.001681070076301694, 0.03693488612771034, -0.08100935816764832, -0.03178160637617111, -0.030177531763911247, -0.020812533795833588, -0.014491626992821693, -0.01819487474858761, -0.00693318247795105, -0.025987470522522926, 0.0203871913254261, 0.03322084620594978, 0.007113815750926733, 0.01175146084278822, 0.011802028864622116, -0.04891163483262062, 0.03362104669213295, -0.07420346140861511, -0.07266935706138611, 0.00424754386767745, -0.05110837519168854, 0.03763461858034134, -0.0029107211157679558, -0.0017669596709311008, -0.009217919781804085, -0.0223727747797966, -0.02276541478931904, -0.005709769204258919, -0.018832406029105186, -0.018558891490101814, 0.09701454639434814, -3.134470171062276e-05, 0.013778149150311947, 0.025061175227165222, 0.06504049152135849, -0.0010301598813384771, -0.0897194966673851, -0.02937312051653862, -0.010941596701741219, 0.0018644781084731221, 0.05590954050421715, 0.026075152680277824, 0.05139530077576637, -0.010917403735220432, 0.00870157778263092, 0.015995193272829056, 0.006445177365094423, 0.04837393760681152, 0.025667952373623848, -0.008727463893592358, -0.029190072789788246, -0.018183276057243347, -0.0621129646897316, 0.020885098725557327, 0.06874728947877884, -0.23344504833221436, -0.02258511632680893, -0.01419254019856453, 0.10320448130369186, -0.005822952836751938, 0.0024899616837501526, 0.023092474788427353, -0.0038407070096582174, -0.013031963258981705, 0.03569323942065239, -0.049997638911008835, 0.029806140810251236, 0.009199211373925209, -0.058769576251506805, -0.03448537364602089, 0.04246056452393532, 0.07039237767457962, -0.04602818936109543, 0.06294197589159012, 0.004651046358048916, -0.001652638427913189, -0.03949356824159622, 0.12305214256048203, -0.02445746771991253, -0.04061185196042061, -0.0042878249660134315, 0.011829865165054798, -0.019710924476385117, 0.028901495039463043, 0.033081069588661194, -0.010725338943302631, -0.02745557762682438, 0.10162729769945145, 0.05656793341040611, 0.016987605020403862, 0.025119241327047348, 0.004949004389345646, -0.061499010771512985, 0.0024393266066908836, 0.01115493569523096, 0.026186874136328697, -0.03403957560658455, 0.015666430816054344, 0.018578195944428444, 0.054081711918115616, 0.009812631644308567, -0.008632104843854904, -0.08555403351783752, 0.00032727871439419687, 0.013853251934051514, -0.04474908858537674, -0.022167515009641647, -0.008224789053201675, 0.01202460192143917, 0.05611058324575424, 0.009806507267057896, 0.03089478611946106, 0.008607840165495872, -0.023285187780857086, -0.045362312346696854, 0.031830571591854095, -0.02046814002096653, 0.01958327554166317, -0.022897496819496155, -0.02404063194990158]}, "text_id_to_ref_doc_id": {"860863cb-ba90-4287-9ff3-de812a7cf04a": "ac226b84-1585-4759-add3-dc5d0af6ef65"}, "metadata_dict": {"860863cb-ba90-4287-9ff3-de812a7cf04a": {"page_label": "1", "file_name": "saved_pdf.pdf", "file_path": "E:\\llama-index RAG\\data\\saved_pdf.pdf", "file_type": "application/pdf", "file_size": 64903, "creation_date": "2024-04-14", "last_modified_date": "2024-04-17", "_node_type": "TextNode", "document_id": "ac226b84-1585-4759-add3-dc5d0af6ef65", "doc_id": "ac226b84-1585-4759-add3-dc5d0af6ef65", "ref_doc_id": "ac226b84-1585-4759-add3-dc5d0af6ef65"}}}

db/docstore.json

@@ -0,0 +1 @@
+{"docstore/metadata": {"ac226b84-1585-4759-add3-dc5d0af6ef65": {"doc_hash": "2c629fa1f2e1e85f17b7d012739aea7cba30cdd55f935ed2225710942132eabf"}, "860863cb-ba90-4287-9ff3-de812a7cf04a": {"doc_hash": "2c629fa1f2e1e85f17b7d012739aea7cba30cdd55f935ed2225710942132eabf", "ref_doc_id": "ac226b84-1585-4759-add3-dc5d0af6ef65"}}, "docstore/data": {"860863cb-ba90-4287-9ff3-de812a7cf04a": {"__data__": {"id_": "860863cb-ba90-4287-9ff3-de812a7cf04a", "embedding": null, "metadata": {"page_label": "1", "file_name": "saved_pdf.pdf", "file_path": "E:\\llama-index RAG\\data\\saved_pdf.pdf", "file_type": "application/pdf", "file_size": 64903, "creation_date": "2024-04-14", "last_modified_date": "2024-04-17"}, "excluded_embed_metadata_keys": ["file_name", "file_type", "file_size", "creation_date", "last_modified_date", "last_accessed_date"], "excluded_llm_metadata_keys": ["file_name", "file_type", "file_size", "creation_date", "last_modified_date", "last_accessed_date"], "relationships": {"1": {"node_id": "ac226b84-1585-4759-add3-dc5d0af6ef65", "node_type": "4", "metadata": {"page_label": "1", "file_name": "saved_pdf.pdf", "file_path": "E:\\llama-index RAG\\data\\saved_pdf.pdf", "file_type": "application/pdf", "file_size": 64903, "creation_date": "2024-04-14", "last_modified_date": "2024-04-17"}, "hash": "2c629fa1f2e1e85f17b7d012739aea7cba30cdd55f935ed2225710942132eabf", "class_name": "RelatedNodeInfo"}}, "text": "3.DataProblem\nThisdocumentoutlinesthespecificinstructionsforpreparingtheprovideddatabaseofhumanvoice\nrecordingsfortrainingamachinelearningmodelcapableofdistinguishingbetweenauthenticand\nsyntheticvoices.\n1.DataExplorationandAnalysis:\n\uf0fc UtilizetoolssuchasMatplotlibandSeabornforin-depthdataanalysisandvisualization.\n\uf0fc Beginwithacomprehensiveexplorationofthedatabase,understandingcharacteristics,and\nassessingthedistributionofauthenticandsyntheticsamples.\n\uf0fc Identifyandaddressimbalancedsamplesinthedataset.\n2.ImbalanceHandling:\n\uf0fc Enhancemodelperformancebyemployingtechniquessuchasoversamplingorundersampling,\ne.g.,usingSMOTEorImblearn.\n3.DataCleaning:\n\uf0fc Addressvariationsinsamplewavlengthbyfindingthemeanoftotalsamplelengths.\n\uf0fc Utilizepaddingtechniquestostandardizeeachsampletothefixedmeanlength.\n\uf0fc Handlemisclassifiedsampleswithinthedataset.\n4.FeatureEngineering:\n\uf0fc ExtractrelevantacousticfeatureslikeMFCCs,spectrograms,andpitchfromaudiorecordings.\n\uf0fc Experimentwithdifferentfeaturesetstoidentifythemostdiscriminativeones.\n\uf0fc Normalizeandstandardizefeaturesforconsistentscaling,facilitatingmodeltraining.\n5.SpeakerEmbeddings:\n\uf0fc Considerincorporatingspeakerembeddingstocaptureindividualcharacteristics,enhancingthe\nmodel'sabilitytogeneralizeacrossdiversevoices.\n\uf0fc Implementsuitablemethodsforextractingspeakerembeddings,suchaspre-trainedmodelsor\ntrainingonthedataset.\n6.DataSplitting:\n\uf0fc Splitthedataintotraining,validation,andtestsets,ensuringastratifiedsplit.\n\uf0fc Evaluatemodelperformanceonthevalidationset,minimizinglossbeforefinaltestingonthe\ntestsamples.\n7.DataAugmentation:\n\uf0fc Applydataaugmentationtechniquestoincreasemodelrobustnessagainstvariationsin\nrecordingconditions.\n\uf0fc Techniquesmayincluderandompitchshifts,time-stretching,orintroducingbackgroundnoise.\n8.QualityControl:\n\uf0fc Conductarigorousqualitycontrolchecktoidentifyandaddressanomaliesoroutliersinthe\ndataset.\n\uf0fc Verifythatdatapreprocessingstepsdonotintroduceartifactsnegativelyaffectingmodel\nperformance.\nOncethedataispreparedfollowingtheseguidelines,thetransitionintothemodeldevelopment\nphasewillfocusonselectinganappropriatearchitecture,trainingthemodel,andfine-tuningitfor\noptimalperformance.", "start_char_idx": 0, "end_char_idx": 2150, "text_template": "{metadata_str}\n\n{content}", "metadata_template": "{key}: {value}", "metadata_seperator": "\n", "class_name": "TextNode"}, "__type__": "1"}}, "docstore/ref_doc_info": {"ac226b84-1585-4759-add3-dc5d0af6ef65": {"node_ids": ["860863cb-ba90-4287-9ff3-de812a7cf04a"], "metadata": {"page_label": "1", "file_name": "saved_pdf.pdf", "file_path": "E:\\llama-index RAG\\data\\saved_pdf.pdf", "file_type": "application/pdf", "file_size": 64903, "creation_date": "2024-04-14", "last_modified_date": "2024-04-17"}}}}

db/graph_store.json

@@ -0,0 +1 @@
+{"graph_dict": {}}

db/image__vector_store.json

@@ -0,0 +1 @@
+{"embedding_dict": {}, "text_id_to_ref_doc_id": {}, "metadata_dict": {}}

db/index_store.json

@@ -0,0 +1 @@
+{"index_store/data": {"01282bcc-a355-4256-b245-78ace39871e9": {"__type__": "vector_store", "__data__": "{\"index_id\": \"01282bcc-a355-4256-b245-78ace39871e9\", \"summary\": null, \"nodes_dict\": {\"860863cb-ba90-4287-9ff3-de812a7cf04a\": \"860863cb-ba90-4287-9ff3-de812a7cf04a\"}, \"doc_id_dict\": {}, \"embeddings_dict\": {}}"}}}

requirements.txt

@@ -0,0 +1,5 @@
+streamlit
+python-dotenv
+llama-index
+llama-index-embeddings-huggingface
+llama-index-llms-huggingface