markdown file query
1.0.0
Proyek ini saat ini bekerja paling baik dengan dokumen bahasa Inggris.
proyek ini
.md apa pun, jadi berfungsi sempurna dengan Notion & Obsidian (meskipun untuk gagasan Anda harus mengekspornya ke .md secara manual)langchain.textsplitterlangchain.embeddings.OpenAIEmbeddings )Pinecone Vector Database.--help export PINECONE_API_KEY= " your_pinecone_api_key "
export OPENAI_API_KEY= " your_openai_api_key " import os
os . environ [ "PINECONE_API_KEY" ]
os . environ [ "OPENAI_API_KEY" ]KeyError , lalu restart terminal setelah selesai (dan IDE Anda jika Anda menggunakannya).git clone https://github.com/madeyexz/markdown-file-query.git pip install pinecone langchain tqdmFOLDER (atau nama apa pun yang Anda sukai, tetapi Anda harus mengubah kode yang sesuai). Perhatikan ini harus berada di direktori yang sama dengan main.pymain.py python3 main.py " PATH_OF_FOLDER " " QUESTION "answer.txt dan contents.txt masing -masing.query_only.py untuk menghindari muncul kembali dokumen. python3 query_only.py " QUESTION "markdown_database yang berisi banyak file .md , saya ingin menanyakan database ini dengan pertanyaan "apa situasi aneh" ❯ python3 main.py " markdown_database " " what's the strange situation " initiating pinecone index...
digesting docs...
uploading datas to pinecone...
92%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████ | 60/65 [00:29<00:02, 1.87it/s]
let's wait for 60 seconds to avoid RateLimitError... (since im not a paid user))
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 60/60 [01:00<00:00, 1.00s/it]
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 65/65 [01:32<00:00, 1.42s/it]
querying pinecone...
querying gpt...
writing results to answer.txt and contents.txt
done! the answer to 'what's the strange situation' is: '
The Strange Situation is a standardized procedure devised by Mary Ainsworth in the 1970s to observe attachment security in children within the context of caregiver relationships. It applies to infants between the age of nine and 18 months and involves a series of eight episodes lasting approximately 3 minutes each, whereby a mother, child and stranger are introduced, separated and reunited. The procedure is used to observe the quality of a young child’s attachment to his or her mother, and can also be applied to other attachment figures, such as God, through the use of Emotionally Focused Therapy (EFT) and religious beliefs, such as the saying “there are no atheists in foxholes”.'
query_only.py untuk menghindari muncul kembali dokumen. ❯ python3 query_only.py " Who is Mary Ainsworth? " connecting to pinecone index...
getting docs
querying pinecone...
querying gpt...
done! the answer to 'Who is Mary Ainsworth?' is: '
Mary Ainsworth was a developmental psychologist who devised the Strange Situation in the 1970s to observe attachment security in children within the context of caregiver relationships. The Strange Situation involves a series of eight episodes lasting approximately 3 minutes each, whereby a mother, child and stranger are introduced, separated and reunited. Ainsworth is also known for her observation that if you want to see the quality of a young child’s attachment to his or her mother, watch what the child does, not when Mother leaves, but when she returns. She is also known for her research on anxious babies and their inability to use their mothers as a secure base.'
Jika Anda menggunakan Pinecone, maka kapan pun Anda ingin meminta dokumen baru (yaitu membuat database baru), Anda mungkin harus membuat indeks Pinecone baru (karena Anda tidak ingin jawaban dari dokumen lama), atau hapus indeks lama. Ini karena Pinecone tidak mendukung memperbarui indeks (belum).
Untuk menghapus indeks lama:
python3 delete_pinecone_index.py NAME_OF_INDEXTeriakan besar ke komunitas open-source untuk memberikan contoh langsung dan tutorial komprehensif!