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 output

Browse source
This commit is contained in:
Ray 2025-08-26 19:10:07 +08:00
parent 985d8f064f
commit 3277f16ae1
1 changed files with 23 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

45
cookbook/pageindex_RAG_simple.ipynb
View file

@ -211,7 +211,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": null,
"metadata": { "metadata": {
"colab": { "colab": {
"base_uri": "https://localhost:8080/" "base_uri": "https://localhost:8080/"
@ -257,7 +257,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 41, "execution_count": null,
"metadata": { "metadata": {
"colab": { "colab": {
"base_uri": "https://localhost:8080/", "base_uri": "https://localhost:8080/",
@ -369,7 +369,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 25, "execution_count": 21,
"metadata": { "metadata": {
"id": "LLHNJAtTcG1O" "id": "LLHNJAtTcG1O"
}, },
@ -409,7 +409,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 26, "execution_count": 57,
"metadata": { "metadata": {
"colab": { "colab": {
"base_uri": "https://localhost:8080/", "base_uri": "https://localhost:8080/",
@ -424,12 +424,13 @@
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Reasoning Process:\n", "Reasoning Process:\n",
"The question asks for the conclusions in the document. The most direct and relevant node is '5.\n", "The question asks for the conclusions in the document. Typically, conclusions are found in sections\n",
"Conclusion, Limitations, and Future Work' (node_id: 0019), as it is specifically dedicated to the\n", "explicitly titled 'Conclusion' or in sections summarizing the findings and implications of the work.\n",
"conclusion and related topics. Other nodes, such as the Abstract (0001), Introduction (0003), and\n", "In this document tree, node 0019 ('5. Conclusion, Limitations, and Future Work') is the most\n",
"Discussion (0018), may contain summary statements or high-level findings, but the explicit\n", "directly relevant, as it is dedicated to the conclusion and related topics. Additionally, the\n",
"conclusions are most likely found in node 0019. Therefore, node 0019 is the primary node likely to\n", "'Abstract' (node 0001) may contain a high-level summary that sometimes includes concluding remarks,\n",
"contain the answer.\n", "but it is less likely to contain the full conclusions. Other sections like 'Discussion' (node 0018)\n",
"may discuss implications but are not explicitly conclusions. Therefore, the primary node is 0019.\n",
"\n", "\n",
"Retrieved Nodes:\n", "Retrieved Nodes:\n",
"Node ID: 0019\t Page: 16\t Title: 5. Conclusion, Limitations, and Future Work\n" "Node ID: 0019\t Page: 16\t Title: 5. Conclusion, Limitations, and Future Work\n"
@ -467,7 +468,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 27, "execution_count": 58,
"metadata": { "metadata": {
"colab": { "colab": {
"base_uri": "https://localhost:8080/", "base_uri": "https://localhost:8080/",
@ -519,7 +520,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 28, "execution_count": 59,
"metadata": { "metadata": {
"colab": { "colab": {
"base_uri": "https://localhost:8080/", "base_uri": "https://localhost:8080/",
@ -535,18 +536,18 @@
"text": [ "text": [
"Generated Answer:\n", "Generated Answer:\n",
"\n", "\n",
"**Conclusions in this document:**\n", "The conclusions in this document are:\n",
"\n", "\n",
"- DeepSeek-R1-Zero, a pure reinforcement learning (RL) model without cold-start data, achieves\n", "- DeepSeek-R1-Zero, a pure reinforcement learning (RL) approach without cold-start data, achieves\n",
"strong performance across various tasks.\n", "strong performance across various tasks.\n",
"- DeepSeek-R1, which combines cold-start data with iterative RL fine-tuning, is even more powerful\n", "- DeepSeek-R1, which combines cold-start data with iterative RL fine-tuning, is more powerful and\n",
"and achieves performance comparable to OpenAI-o1-1217 on a range of tasks.\n", "achieves performance comparable to OpenAI-o1-1217 on a range of tasks.\n",
"- The reasoning capabilities of DeepSeek-R1 can be successfully distilled into smaller dense models,\n", "- Distilling DeepSeek-R1’s reasoning capabilities into smaller dense models is promising; for\n",
"with DeepSeek-R1-Distill-Qwen-1.5B outperforming GPT-4o and Claude-3.5-Sonnet on math benchmarks.\n", "example, DeepSeek-R1-Distill-Qwen-1.5B outperforms GPT-4o and Claude-3.5-Sonnet on math benchmarks,\n",
"- Other small dense models fine-tuned with DeepSeek-R1 data also significantly outperform other\n", "and other dense models also show significant improvements over similar instruction-tuned models.\n",
"instruction-tuned models based on the same checkpoints.\n", "\n",
"- Overall, the approaches described demonstrate promising results in enhancing model reasoning\n", "These results demonstrate the effectiveness of the RL-based approach and the potential for\n",
"abilities through RL and distillation.\n" "distilling reasoning abilities into smaller models.\n"
] ]
} }
], ],