apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-04-24 23:56:21 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

fix notebook format

Browse source
This commit is contained in:
Ray 2025-08-22 01:11:48 +08:00
parent e0edea6d51
commit cf0a599cff
1 changed files with 37 additions and 25 deletions
Download patch file Download diff file Expand all files Collapse all files

62
cookbook/pageindex_RAG_simple.ipynb
View file

@ -124,7 +124,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 19, "execution_count": 51,
"metadata": { "metadata": {
"id": "hmj3POkDcG1N" "id": "hmj3POkDcG1N"
}, },
@ -154,7 +154,8 @@
" pprint(cleaned_tree, sort_dicts=False, width=100)\n", " pprint(cleaned_tree, sort_dicts=False, width=100)\n",
"\n", "\n",
"def show(text, width=100):\n", "def show(text, width=100):\n",
" print(textwrap.fill(text, width=width))\n", " for line in text.splitlines():\n",
" print(textwrap.fill(line, width=width))\n",
"\n", "\n",
"def create_node_mapping(tree):\n", "def create_node_mapping(tree):\n",
" \"\"\"Create a mapping of node_id to node for quick lookup\"\"\"\n", " \"\"\"Create a mapping of node_id to node for quick lookup\"\"\"\n",
@ -233,7 +234,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 20, "execution_count": 61,
"metadata": { "metadata": {
"colab": { "colab": {
"base_uri": "https://localhost:8080/", "base_uri": "https://localhost:8080/",
@ -390,7 +391,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 35, "execution_count": 57,
"metadata": { "metadata": {
"colab": { "colab": {
"base_uri": "https://localhost:8080/", "base_uri": "https://localhost:8080/",
@ -449,7 +450,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 37, "execution_count": 58,
"metadata": { "metadata": {
"colab": { "colab": {
"base_uri": "https://localhost:8080/", "base_uri": "https://localhost:8080/",
@ -464,17 +465,23 @@
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Retrieved Context:\n", "Retrieved Context:\n",
"## 5. Conclusion, Limitations, and Future Work In this work, we share our journey in enhancing\n", "\n",
"model reasoning abilities through reinforcement learning. DeepSeek-R1-Zero represents a pure RL\n", "## 5. Conclusion, Limitations, and Future Work\n",
"approach without relying on cold-start data, achieving strong performance across various tasks.\n", "\n",
"DeepSeek-R1 is more powerful, leveraging cold-start data alongside iterative RL fine-tuning.\n", "In this work, we share our journey in enhancing model reasoning abilities through reinforcement\n",
"Ultimately, DeepSeek-R1 achieves performance comparable to OpenAI-o1-1217 on a range of tasks. We\n", "learning. DeepSeek-R1-Zero represents a pure RL approach without relying on cold-start data,\n",
"further explore distillation the reasoning capability to small dense models. We use DeepSeek-R1 as\n", "achieving strong performance across various tasks. DeepSeek-R1 is more powerful, leveraging cold-\n",
"the teacher model to generate 800K training samples, and fine-tune several small dense models. The\n", "start data alongside iterative RL fine-tuning. Ultimately, DeepSeek-R1 achieves performance\n",
"results are promising: DeepSeek-R1-Distill-Qwen-1.5B outperforms GPT-4o and Claude-3.5-Sonnet on\n", "comparable to OpenAI-o1-1217 on a range of tasks.\n",
"\n",
"We further explore distillation the reasoning capability to small dense models. We use DeepSeek-R1\n",
"as the teacher model to generate 800K training samples, and fine-tune several small dense models.\n",
"The results are promising: DeepSeek-R1-Distill-Qwen-1.5B outperforms GPT-4o and Claude-3.5-Sonnet on\n",
"math benchmarks with $28.9 \\%$ on AIME and $83.9 \\%$ on MATH. Other dense models also achieve\n", "math benchmarks with $28.9 \\%$ on AIME and $83.9 \\%$ on MATH. Other dense models also achieve\n",
"impressive results, significantly outperforming other instructiontuned models based on the same\n", "impressive results, significantly outperforming other instructiontuned models based on the same\n",
"underlying checkpoints. In the fut...\n" "underlying checkpoints.\n",
"\n",
"In the fut...\n"
] ]
} }
], ],
@ -482,7 +489,7 @@
"node_list = json.loads(tree_search_result)[\"node_list\"]\n", "node_list = json.loads(tree_search_result)[\"node_list\"]\n",
"relevant_content = \"\\n\\n\".join(node_map[node_id][\"text\"] for node_id in node_list)\n", "relevant_content = \"\\n\\n\".join(node_map[node_id][\"text\"] for node_id in node_list)\n",
"\n", "\n",
"print('Retrieved Context:')\n", "print('Retrieved Context:\\n')\n",
"show(relevant_content[:1000] + '...')" "show(relevant_content[:1000] + '...')"
] ]
}, },
@ -495,7 +502,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 36, "execution_count": 59,
"metadata": { "metadata": {
"colab": { "colab": {
"base_uri": "https://localhost:8080/", "base_uri": "https://localhost:8080/",
@ -510,14 +517,19 @@
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Generated Answer:\n", "Generated Answer:\n",
"**Conclusions in this document:** - DeepSeek-R1-Zero, a pure reinforcement learning (RL) model\n", "\n",
"without cold-start data, achieves strong performance across various tasks. - DeepSeek-R1, which\n", "The conclusions in this document are:\n",
"combines cold-start data with iterative RL fine-tuning, is even more powerful and achieves\n", "\n",
"performance comparable to OpenAI-o1-1217 on a range of tasks. - Distilling DeepSeek-R1’s reasoning\n", "- DeepSeek-R1-Zero, a pure reinforcement learning (RL) approach without cold-start data, achieves\n",
"capabilities into smaller dense models is effective: DeepSeek-R1-Distill-Qwen-1.5B outperforms\n", "strong performance across various tasks.\n",
"GPT-4o and Claude-3.5-Sonnet on math benchmarks, and other dense models also show significant\n", "- DeepSeek-R1, which combines cold-start data with iterative RL fine-tuning, is more powerful and\n",
"improvements over similar instruction-tuned models. - Overall, the approaches described demonstrate\n", "achieves performance comparable to OpenAI-o1-1217 on a range of tasks.\n",
"promising results in enhancing model reasoning abilities through RL and distillation.\n" "- Distilling DeepSeek-R1’s reasoning capabilities into smaller dense models is promising; for\n",
"example, DeepSeek-R1-Distill-Qwen-1.5B outperforms GPT-4o and Claude-3.5-Sonnet on math benchmarks,\n",
"and other dense models also show significant improvements over similar instruction-tuned models.\n",
"\n",
"These results demonstrate the effectiveness of the RL-based approach and the potential for\n",
"distilling reasoning abilities into smaller models.\n"
] ]
} }
], ],
@ -531,7 +543,7 @@
"Provide a clear, concise answer based only on the context provided.\n", "Provide a clear, concise answer based only on the context provided.\n",
"\"\"\"\n", "\"\"\"\n",
"\n", "\n",
"print('Generated Answer:')\n", "print('Generated Answer:\\n')\n",
"answer = await call_llm(answer_prompt)\n", "answer = await call_llm(answer_prompt)\n",
"show(answer)" "show(answer)"
] ]