RAZVOJ ČET BOTA SA DUGOROČNIM PAMĆENJEM I RAZUMEVANJEM KONTEKSTA
Ključne reči:
čet botovi, vektorske baze podataka, dugoročna memorija, jezički modeli
Apstrakt
U ovom radu će biti predstavljen razvoj čet bota koji je u stanju da dugoročno pamti i razume kontekst započete prepiske. Rad uključuje opis korišćenih tehnika i načina na koji su povezani zarad dobijanja sistema koji simulira ljudsku interakciju.
Reference
[1] Brown, Hannah, Katherine Lee, Fatemehsadat Mireshghallah, Reza Shokri, and Florian Tramèr. "What does it mean for a language model to preserve privacy?." In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, pp. 2280-229.
[2] Lund, Brady D., and Ting Wang. "Chatting about ChatGPT: how may AI and GPT impact academia and libraries?." Library Hi Tech News 40, no. 3 (2023): 26-29.
[3] Liu, Yiheng, Tianle Han, Siyuan Ma, Jiayue Zhang, Yuanyuan Yang, Jiaming Tian, Hao He et al. "Summary of chatgpt/gpt-4 research and perspective towards the future of large language models." arXiv preprint arXiv:2304.01852 (2023).
[4] https://www.pinecone.io/learn/vector-database (pristupljeno u septembru 2023.)
[5] https://www.pinecone.io/learn/vector-embeddings-for-developers (pristupljeno u septembru 2023.)
[6] https://python.langchain.com/docs/get_started/ introduction (pristupljeno u septembru 2023.)
[7] https://python.langchain.com/docs/modules/mo
del_io/models (pristupljeno u septembru 2023.)
[8] Topsakal, Oguzhan, and Tahir Cetin Akinci. "Creating Large Language Model Applications Utilizing LangChain: A Primer on Developing LLM Apps Fast." In International Conference on Applied Engineering and Natural Sciences, vol. 1, no. 1, pp. 1050-1056. 2023.
[9] https://learn.deeplearning.ai/langchain/lesson/3/m
emory (pristupljeno u septembru 2023.)
[10] https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them (pristupljeno u septembru 2023.)
[11] https://python.langchain.com/docs/modules/agents (pristupljeno u septembru 2023.)
[12] https://github.com/getzep/zep (pristupljeno u septembru 2023.)
[13] https://www.python.org (pristupljeno u septembru 2023.)
[14] https://telegram.org (pristupljeno u septembru 2023.)
[2] Lund, Brady D., and Ting Wang. "Chatting about ChatGPT: how may AI and GPT impact academia and libraries?." Library Hi Tech News 40, no. 3 (2023): 26-29.
[3] Liu, Yiheng, Tianle Han, Siyuan Ma, Jiayue Zhang, Yuanyuan Yang, Jiaming Tian, Hao He et al. "Summary of chatgpt/gpt-4 research and perspective towards the future of large language models." arXiv preprint arXiv:2304.01852 (2023).
[4] https://www.pinecone.io/learn/vector-database (pristupljeno u septembru 2023.)
[5] https://www.pinecone.io/learn/vector-embeddings-for-developers (pristupljeno u septembru 2023.)
[6] https://python.langchain.com/docs/get_started/ introduction (pristupljeno u septembru 2023.)
[7] https://python.langchain.com/docs/modules/mo
del_io/models (pristupljeno u septembru 2023.)
[8] Topsakal, Oguzhan, and Tahir Cetin Akinci. "Creating Large Language Model Applications Utilizing LangChain: A Primer on Developing LLM Apps Fast." In International Conference on Applied Engineering and Natural Sciences, vol. 1, no. 1, pp. 1050-1056. 2023.
[9] https://learn.deeplearning.ai/langchain/lesson/3/m
emory (pristupljeno u septembru 2023.)
[10] https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them (pristupljeno u septembru 2023.)
[11] https://python.langchain.com/docs/modules/agents (pristupljeno u septembru 2023.)
[12] https://github.com/getzep/zep (pristupljeno u septembru 2023.)
[13] https://www.python.org (pristupljeno u septembru 2023.)
[14] https://telegram.org (pristupljeno u septembru 2023.)
Objavljeno
2024-03-02
Sekcija
Elektrotehničko i računarsko inženjerstvo
