{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HGEBMABTJNFYH6QJTG35TNRIJO","short_pith_number":"pith:HGEBMABT","schema_version":"1.0","canonical_sha256":"39881600334b4b83fa0999b7d9b6284b9bcba748ab4d2a97f515e51d10c24d46","source":{"kind":"arxiv","id":"2408.05933","version":1},"attestation_state":"computed","paper":{"title":"Optimizing RAG Techniques for Automotive Industry PDF Chatbots: A Case Study with Locally Deployed Ollama Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.IR","authors_text":"Fei Liu, Xing Han, Zejun Kang","submitted_at":"2024-08-12T06:16:37Z","abstract_excerpt":"With the growing demand for offline PDF chatbots in automotive industrial production environments, optimizing the deployment of large language models (LLMs) in local, low-performance settings has become increasingly important. This study focuses on enhancing Retrieval-Augmented Generation (RAG) techniques for processing complex automotive industry documents using locally deployed Ollama models. Based on the Langchain framework, we propose a multi-dimensional optimization approach for Ollama's local RAG implementation. Our method addresses key challenges in automotive document processing, inclu"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2408.05933","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-12T06:16:37Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"e06eaaad2ed01ac98d9e860756a6c01c12acedb03a7efbf1672189f8a03e2c09","abstract_canon_sha256":"0588df53402b5015119daad897e43929f69b64a3acd07b0294736c956396110b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:27.171432Z","signature_b64":"1GjXwOP4mOxOuNs52dQKyYgo5tX5Vhg+WKofXZ8aWZci4SBagA9+J7pMEb3JjZL6ENy96FnJWJdLQcqAnOQTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39881600334b4b83fa0999b7d9b6284b9bcba748ab4d2a97f515e51d10c24d46","last_reissued_at":"2026-07-05T08:54:27.170971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:27.170971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing RAG Techniques for Automotive Industry PDF Chatbots: A Case Study with Locally Deployed Ollama Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.IR","authors_text":"Fei Liu, Xing Han, Zejun Kang","submitted_at":"2024-08-12T06:16:37Z","abstract_excerpt":"With the growing demand for offline PDF chatbots in automotive industrial production environments, optimizing the deployment of large language models (LLMs) in local, low-performance settings has become increasingly important. This study focuses on enhancing Retrieval-Augmented Generation (RAG) techniques for processing complex automotive industry documents using locally deployed Ollama models. Based on the Langchain framework, we propose a multi-dimensional optimization approach for Ollama's local RAG implementation. Our method addresses key challenges in automotive document processing, inclu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05933","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2408.05933/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2408.05933","created_at":"2026-07-05T08:54:27.171027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.05933v1","created_at":"2026-07-05T08:54:27.171027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05933","created_at":"2026-07-05T08:54:27.171027+00:00"},{"alias_kind":"pith_short_12","alias_value":"HGEBMABTJNFY","created_at":"2026-07-05T08:54:27.171027+00:00"},{"alias_kind":"pith_short_16","alias_value":"HGEBMABTJNFYH6QJ","created_at":"2026-07-05T08:54:27.171027+00:00"},{"alias_kind":"pith_short_8","alias_value":"HGEBMABT","created_at":"2026-07-05T08:54:27.171027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11995","citing_title":"Combining Large Language Models with Tutoring System Intelligence: A Case Study in Caregiver Homework Support","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HGEBMABTJNFYH6QJTG35TNRIJO","json":"https://pith.science/pith/HGEBMABTJNFYH6QJTG35TNRIJO.json","graph_json":"https://pith.science/api/pith-number/HGEBMABTJNFYH6QJTG35TNRIJO/graph.json","events_json":"https://pith.science/api/pith-number/HGEBMABTJNFYH6QJTG35TNRIJO/events.json","paper":"https://pith.science/paper/HGEBMABT"},"agent_actions":{"view_html":"https://pith.science/pith/HGEBMABTJNFYH6QJTG35TNRIJO","download_json":"https://pith.science/pith/HGEBMABTJNFYH6QJTG35TNRIJO.json","view_paper":"https://pith.science/paper/HGEBMABT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.05933&json=true","fetch_graph":"https://pith.science/api/pith-number/HGEBMABTJNFYH6QJTG35TNRIJO/graph.json","fetch_events":"https://pith.science/api/pith-number/HGEBMABTJNFYH6QJTG35TNRIJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HGEBMABTJNFYH6QJTG35TNRIJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HGEBMABTJNFYH6QJTG35TNRIJO/action/storage_attestation","attest_author":"https://pith.science/pith/HGEBMABTJNFYH6QJTG35TNRIJO/action/author_attestation","sign_citation":"https://pith.science/pith/HGEBMABTJNFYH6QJTG35TNRIJO/action/citation_signature","submit_replication":"https://pith.science/pith/HGEBMABTJNFYH6QJTG35TNRIJO/action/replication_record"}},"created_at":"2026-07-05T08:54:27.171027+00:00","updated_at":"2026-07-05T08:54:27.171027+00:00"}