feat: make new flowchart&result chart

denser-org · May 27, 2024 · b69979a · b69979a
1 parent 30b9734
commit b69979a
Show file tree

Hide file tree

Showing 10 changed files with 149 additions and 53 deletions.
diff --git a/README.md b/README.md
@@ -29,7 +29,7 @@ xgboost)** machine learning technique to combines:
 
 We show that the combinations can significantly improve the retrieval accuracy on MTEB benchmarks when compared to each individual retrievers.
 
-![](./www/pages/docs/experiments/RAG-flow-data.png)
+![](./www/content/docs/experiments/rag-flow-data.png)
 
 ## 🚀 Features
 

diff --git a/bun.lockb b/bun.lockb
diff --git a/www/app/global.css b/www/app/global.css
@@ -542,3 +542,7 @@ details > summary::before {
 details[open] > summary::before {
   transform: rotate(90deg);
 }
+
+.prose table th {
+  @apply text-left;
+}
diff --git a/www/components/mteb-chart.tsx b/www/components/mteb-chart.tsx
@@ -0,0 +1,77 @@
+"use client"
+
+import {
+  Bar,
+  BarChart,
+  CartesianGrid,
+  Legend,
+  Rectangle,
+  ResponsiveContainer,
+  Tooltip,
+  XAxis,
+  YAxis,
+} from "recharts"
+
+export interface MtebChartProps {
+  data: any
+}
+
+export default function MtebChart({ data }: MtebChartProps) {
+  return (
+    <ResponsiveContainer width="100%" height={400}>
+      <BarChart
+        width={500}
+        height={300}
+        data={data}
+        margin={{
+          top: 5,
+          right: 30,
+          left: 20,
+          bottom: 5,
+        }}
+      >
+        <CartesianGrid strokeDasharray="3 3" />
+        <XAxis
+          dataKey="name"
+          fontSize="10px"
+          interval={0}
+          angle={-45}
+          textAnchor="end"
+        />
+        <YAxis fontSize={12} />
+        <Tooltip
+          contentStyle={{
+            fontSize: "12px",
+            backgroundColor: "rgba(255, 255, 255, 0.9)",
+            border: "1px solid #f5f5f5",
+            borderRadius: "4px",
+            boxShadow: "0 2px 4px 0 rgba(0,0,0,0.1)",
+          }}
+        />
+
+        <Legend
+          formatter={(value) => {
+            if (value === "evrn") return "ES+VS+RR_n"
+            return value.toUpperCase()
+          }}
+          wrapperStyle={{
+            paddingTop: "1rem",
+            fontSize: "12px",
+          }}
+        />
+        <Bar
+          dataKey="es"
+          fill="#519DE9"
+        />
+        <Bar
+          dataKey="vs"
+          fill="#7CC674"
+        />
+        <Bar
+          dataKey="ES+VS+RR_n"
+          fill="#F4C145"
+        />
+      </BarChart>
+    </ResponsiveContainer>
+  )
+}
diff --git a/www/content/docs/experiments/RAG-flow-data.png b/www/content/docs/experiments/RAG-flow-data.png
diff --git a/www/content/docs/experiments/mteb_ndcg_plot.png b/www/content/docs/experiments/mteb_ndcg_plot.png
diff --git a/www/content/docs/experiments/mteb_retrieval.mdx b/www/content/docs/experiments/mteb_retrieval.mdx
@@ -3,35 +3,36 @@ title: MTEB Retrieval Experiments
 ---
 
 <Callout type="info">
-  We run this experiment on a **server**, which requires ES and Milvus installations specified [here](/docs/install/install-server).
+  We run this experiment on a **server**, which requires ES and Milvus
+  installations specified [here](/docs/install/install-server).
 </Callout>
 
-
-
 ## MTEB datasets
+
 MTEB [retrieval datasets](https://github.com/embeddings-benchmark/mteb) consists of 15 datasets. The datasets stats including name, corpus size, train, dev and test query sizes are listed in the following table.
 
-|Name |#Corpus | #Train Query | #Dev Query | #Test Query|
-|---|---|---|---|---|
-|ArguAna |8,674 |0 |0 |1,406|
-|ClimateFEVER |5,416,593 | 0 |0 |1,535|
-|CQADupstack |457,199 |0 |0 |9,963|
-|DBPedia |4,635,922|0 |67 |400 |
-|FEVER |5,416,568 |109,810| 6,666 |6,666 |
-|FiQA2018 |57,638| 5,500 |500 |648|
-|HotpotQA| 5,233,329 |85,000 | 5,447 |7,405 |
-|MSMARCO |8,841,823| 502,939 |6,980 |43|
-|NFCorpus |3,633|  2,590 |324 |323 |
-|NQ| 2,681,468| 0 | 0 |3,452 |
-|QuoraRetrieval |522,931| 0 |5,000 |10,000|
-|SCIDOCS |25,657| 0 |0 |1,000 |
-|SciFact|5,183| 809 |0 |300 |
-|Touche2020 |382,545| 0 |0 |49 |
-|TRECCOVID | 171,332| 0 |0 |50 |
+| Name           | #Corpus   | #Train Query | #Dev Query | #Test Query |
+| -------------- | --------- | ------------ | ---------- | ----------- |
+| ArguAna        | 8,674     | 0            | 0          | 1,406       |
+| ClimateFEVER   | 5,416,593 | 0            | 0          | 1,535       |
+| CQADupstack    | 457,199   | 0            | 0          | 9,963       |
+| DBPedia        | 4,635,922 | 0            | 67         | 400         |
+| FEVER          | 5,416,568 | 109,810      | 6,666      | 6,666       |
+| FiQA2018       | 57,638    | 5,500        | 500        | 648         |
+| HotpotQA       | 5,233,329 | 85,000       | 5,447      | 7,405       |
+| MSMARCO        | 8,841,823 | 502,939      | 6,980      | 43          |
+| NFCorpus       | 3,633     | 2,590        | 324        | 323         |
+| NQ             | 2,681,468 | 0            | 0          | 3,452       |
+| QuoraRetrieval | 522,931   | 0            | 5,000      | 10,000      |
+| SCIDOCS        | 25,657    | 0            | 0          | 1,000       |
+| SciFact        | 5,183     | 809          | 0          | 300         |
+| Touche2020     | 382,545   | 0            | 0          | 49          |
+| TRECCOVID      | 171,332   | 0            | 0          | 50          |
 
 ## Train and test xgboost models
 
 For each dataset in [MTEB](https://github.com/embeddings-benchmark/mteb), we trained an xgboost models on the training dataset and tested on the test dataset. To speed up the experiments, we used up to 10k queries per dataset in training (`max_query_size: 10000` in `config_server.yaml`). For datasets which do not have training data, we used the development data to train. If neither training nor development data exists, we applied the 3-fold cross-validation. That is, we randomly split the test data into three folds, we used two folds to train a xgboost model and tested on the third fold. We applied this process three times so the whole test dataset can be evaluated. We fixed the xgboost model training with the following settings. Specifically, we used the ndcg metric as model update objective, a moderate learning rate (`eta`) of 0.1, regularization parameter (`gamma`) of 1.0, `min_child_weight` of 0.1, maximum depth of tree up to 6, and evaluation metric of ndcg@10. We used a fixed number (100) of boosting iterations (`num_boost_round`), thus no attempting to optimize the training per dataset.
+
 ```python
 params = {
                 "objective": "rank:ndcg",
@@ -42,6 +43,7 @@ params = {
                 "eval_metric": "ndcg@10",
             }
 ```
+
 The source code for the experiment can be found at [train_and_test.py](https://github.com/denser-org/denser-retriever/blob/main/experiments/train_and_test.py). We ran the following command to train 8 xgboost models (ES+VS, ES+RR, VS+RR, ES+VS+RR, ES+VS_n, ES+RR_n, VS+RR_n, and ES+VS+RR_n) using MSMARCO training data. The definitions of these 8 models can be found at [training](./training). The parameters are dataset_name, train split, and test split respectively.
 
 ```shell
@@ -69,49 +71,58 @@ We can then evaluate the MTEB dataset (MSMARCO as an example) by running:
 ```shell
 poetry run python experiments/test.py mteb/msmarco
 ```
+
 We will get the ndcg@10 score after the evaluation.
 
 ## Experiment results
 
 We list the ndcg@10 scores of different models in the following table. Ref is the reference ndcg@10 of `snowflake-arctic-embed-m` from Huggingface [leaderboard](https://huggingface.co/spaces/mteb/leaderboard), which is consistent with our reported VS accuracy. The bold numbers are the highest accuracy per dataset in our experiments. We use VS instead of Ref as the vector search baseline. Delta and % are the ndcg@10 absolute and relative gains of ES+VS+RR_n model compared to VS baseline.
 
-|Name | ES | VS | ES+VS/ES+VS_n | ES+RR/ES+RR_n | VS+RR/VS+RR_n | ES+VS+RR/ES+VS+RR_n |Ref | Delta/%|
-|---|---|---|---|---|---|---|---|---|
-|ArguAna |42.93 |56.49 | 56.68/57.27 |47.45/48.21 | 56.32/56.44 |56.81/**57.28** |56.44 | 0.79/1.39% |
-|ClimateFEVER |18.10 |39.12 | 39.21/39.01 |28.20/28.34 | 39.06/38.71 |39.11/**39.25** |39.37 |0.13/0.33%|
-|CQADupstack |25.13 | 42.23 | 42.40/42.51 |37.68/37.54 | 43.92/44.25 |43.85/**44.32** |43.81 | 2.09/4.94%|
-|DBPedia |27.42 |44.66 | 45.26/44.26 |47.94/48.26 | 48.62/49.08 |48.79/**49.13** |44.73 | 4.47/10.00% |
-|FEVER |72.80 |88.90 | 89.29/90.05 |84.38/84.94 | 89.84/90.30 |90.21/**91.00** |89.02 | 2.10/2.36%|
-|FiQA2018 |23.89 |42.29 | 42.57/42.79 |36.62/36.31 | 43.04/43.09 |43.19/**43.22** |42.4 | 0.93/2.19%|
-|HotpotQA|54.94 |73.65 | 74.74/75.01 |74.93/75.39 | 77.64/78.07 |77.95/**78.37** |73.65 |4.72/6.40% |
-|MSMARCO |21.84 |41.77 | 41.65/41.72 |46.93/47.15 | 47.11/**47.24** |47.09/47.23 | 41.77 | 5.46/13.07% |
-|NFCorpus |31.40 |36.74 | 37.37/37.63 |34.51/35.36 | 37.32/37.31 |**37.70**/37.15 |36.77 | 0.41/1.11% |
-|NQ|27.21 |61.33 | 60.51/61.20 |55.60/55.47 | 61.50/62.24 |62.27/**62.35** | 62.43 | 1.02/1.66% |
-|QuoraRetrieval|74.23 |80.73 | 86.64/86.91 |84.14/84.40 | 87.76/88.10 |88.39/**88.54** | 87.42 | 7.81/9.67% |
-|SCIDOCS |14.68 |21.03 | 20.49/20.06 |16.48/16.48 | **20.51**/20.19 |20.34/20.03 |21.10 | -1.00/-4.75% |
-|SciFact|58.42 |73.16 | 73.28/75.08 | 69.08/69.69 | 72.73/73.62 |73.08/**75.33** |73.55 | 2.17/2.96% |
-|Touche2020 |29.92 |**32.65** | 31.86/34.26 |29.76/29.93 | 30.47/29.30 |31.51/30.98 |31.47 | -1.67/-5.11% |
-|TRECCOVID |52.02 |78.92 | 77.78/79.12 |75.59/76.95 | 80.34/81.19 |81.97/**83.01** |79.65 | 4.09/5.18% |
-|Average |38.32 |54.24 |54.64/55.12 |51.28/51.62| 55.74/55.94 |56.15/**56.47** | 54.91 |2.23/4.11%|
-
-![](./mteb_ndcg_plot.png)
+| Name           | ES    | VS        | ES+VS/ES+VS_n | ES+RR/ES+RR_n | VS+RR/VS+RR_n   | ES+VS+RR/ES+VS+RR_n | Ref   | Delta/%      |
+| -------------- | ----- | --------- | ------------- | ------------- | --------------- | ------------------- | ----- | ------------ |
+| ArguAna        | 42.93 | 56.49     | 56.68/57.27   | 47.45/48.21   | 56.32/56.44     | 56.81/**57.28**     | 56.44 | 0.79/1.39%   |
+| ClimateFEVER   | 18.10 | 39.12     | 39.21/39.01   | 28.20/28.34   | 39.06/38.71     | 39.11/**39.25**     | 39.37 | 0.13/0.33%   |
+| CQADupstack    | 25.13 | 42.23     | 42.40/42.51   | 37.68/37.54   | 43.92/44.25     | 43.85/**44.32**     | 43.81 | 2.09/4.94%   |
+| DBPedia        | 27.42 | 44.66     | 45.26/44.26   | 47.94/48.26   | 48.62/49.08     | 48.79/**49.13**     | 44.73 | 4.47/10.00%  |
+| FEVER          | 72.80 | 88.90     | 89.29/90.05   | 84.38/84.94   | 89.84/90.30     | 90.21/**91.00**     | 89.02 | 2.10/2.36%   |
+| FiQA2018       | 23.89 | 42.29     | 42.57/42.79   | 36.62/36.31   | 43.04/43.09     | 43.19/**43.22**     | 42.4  | 0.93/2.19%   |
+| HotpotQA       | 54.94 | 73.65     | 74.74/75.01   | 74.93/75.39   | 77.64/78.07     | 77.95/**78.37**     | 73.65 | 4.72/6.40%   |
+| MSMARCO        | 21.84 | 41.77     | 41.65/41.72   | 46.93/47.15   | 47.11/**47.24** | 47.09/47.23         | 41.77 | 5.46/13.07%  |
+| NFCorpus       | 31.40 | 36.74     | 37.37/37.63   | 34.51/35.36   | 37.32/37.31     | **37.70**/37.15     | 36.77 | 0.41/1.11%   |
+| NQ             | 27.21 | 61.33     | 60.51/61.20   | 55.60/55.47   | 61.50/62.24     | 62.27/**62.35**     | 62.43 | 1.02/1.66%   |
+| QuoraRetrieval | 74.23 | 80.73     | 86.64/86.91   | 84.14/84.40   | 87.76/88.10     | 88.39/**88.54**     | 87.42 | 7.81/9.67%   |
+| SCIDOCS        | 14.68 | 21.03     | 20.49/20.06   | 16.48/16.48   | **20.51**/20.19 | 20.34/20.03         | 21.10 | -1.00/-4.75% |
+| SciFact        | 58.42 | 73.16     | 73.28/75.08   | 69.08/69.69   | 72.73/73.62     | 73.08/**75.33**     | 73.55 | 2.17/2.96%   |
+| Touche2020     | 29.92 | **32.65** | 31.86/34.26   | 29.76/29.93   | 30.47/29.30     | 31.51/30.98         | 31.47 | -1.67/-5.11% |
+| TRECCOVID      | 52.02 | 78.92     | 77.78/79.12   | 75.59/76.95   | 80.34/81.19     | 81.97/**83.01**     | 79.65 | 4.09/5.18%   |
+| Average        | 38.32 | 54.24     | 54.64/55.12   | 51.28/51.62   | 55.74/55.94     | 56.15/**56.47**     | 54.91 | 2.23/4.11%   |
+
+import MtedResult from "./mted_result.json"
+import MtebChart from "@/components/mteb-chart"
+
+<div className="border rounded-md px-1 py-6 mt-10">
+<MtebChart data={MtedResult.slice(0, -1).map(item => ({
+  name: item.Name,
+  es: item.ES.replaceAll("*", ""),
+  vs: item.VS.replaceAll("*", ""),
+  "ES+VS+RR_n": item["ES+VS+RR/ES+VS+RR_n"].split("/")[1].replaceAll("*", ""),
+}))} />
+</div>
 
 Here are the observations from the experiment results.
 
 Vector search with [snowflake-arctic-embed-m](https://github.com/Snowflake-Labs/arctic-embed?tab=readme-ov-file) model can significantly boost the elasticsearch NDCG@10 baseline from 38.32 to 54.24. The combination of elasticsearch, vector search and a reranker via xgboost models can further improve the vector search baseline. For instance, the ES+VS+RR_n model achieves the highest NDCG@10 score of 56.47, surpassing the vector search baseline by an absolute increase of 2.23 and a relative improvement of 4.11%.
 
 For datasets which have training data (FEVER, FiQA2018, HotpotQA, NFCorpus, and SciFact), the combinations of elasticsearch, vector search and reranker via xgboost models are more beneficial, which can be witnessed by the following table.
 
-|Name | VS | ES+VS+RR_n | Delta | Delta%|
-|---|---|---|---|---|
-|FEVER	 |88.9| 91.00|2.10| 2.36|
-|FiQA2018|42.29|43.22|0.93 |2.19 |
-|HotpotQA |73.65 | 78.37 |	4.72	|6.4|
-|MSMARCO	| 41.77 | 47.23 |5.46	|13.07|
-|NFCorpus	|36.74|37.15|0.41	|1.11|
-|SciFact| 73.16| 75.33|	2.17	|2.96|
-|Average | 59.41 | 62.05 |	2.63	| 4.68 |
+| Name     | VS    | ES+VS+RR_n | Delta | Delta% |
+| -------- | ----- | ---------- | ----- | ------ |
+| FEVER    | 88.9  | 91.00      | 2.10  | 2.36   |
+| FiQA2018 | 42.29 | 43.22      | 0.93  | 2.19   |
+| HotpotQA | 73.65 | 78.37      | 4.72  | 6.4    |
+| MSMARCO  | 41.77 | 47.23      | 5.46  | 13.07  |
+| NFCorpus | 36.74 | 37.15      | 0.41  | 1.11   |
+| SciFact  | 73.16 | 75.33      | 2.17  | 2.96   |
+| Average  | 59.41 | 62.05      | 2.63  | 4.68   |
 
 The ES+VS+RR_n model improves the vector search NDCG@10 baseline by 2.63 absolute and 4.68% relative gains on these five datasets. It is worth noting that, on the widely used benchmark dataset MSMARCO, the ES+VS+RR_n leads significant relative NDCG@10 gian of 13.07% when compared to vector search baseline.
-
-
diff --git a/www/content/docs/experiments/mted_result.json b/www/content/docs/experiments/mted_result.json
@@ -0,0 +1 @@
+[{"Name":"ArguAna","ES":"42.93","VS":"56.49","ES+VS/ES+VS_n":"56.68/57.27","ES+RR/ES+RR_n":"47.45/48.21","VS+RR/VS+RR_n":"56.32/56.44","ES+VS+RR/ES+VS+RR_n":"56.81/**57.28**","Ref":"56.44","Delta/%":"0.79/1.39%"},{"Name":"ClimateFEVER","ES":"18.10","VS":"39.12","ES+VS/ES+VS_n":"39.21/39.01","ES+RR/ES+RR_n":"28.20/28.34","VS+RR/VS+RR_n":"39.06/38.71","ES+VS+RR/ES+VS+RR_n":"39.11/**39.25**","Ref":"39.37","Delta/%":"0.13/0.33%"},{"Name":"CQADupstack","ES":"25.13","VS":"42.23","ES+VS/ES+VS_n":"42.40/42.51","ES+RR/ES+RR_n":"37.68/37.54","VS+RR/VS+RR_n":"43.92/44.25","ES+VS+RR/ES+VS+RR_n":"43.85/**44.32**","Ref":"43.81","Delta/%":"2.09/4.94%"},{"Name":"DBPedia","ES":"27.42","VS":"44.66","ES+VS/ES+VS_n":"45.26/44.26","ES+RR/ES+RR_n":"47.94/48.26","VS+RR/VS+RR_n":"48.62/49.08","ES+VS+RR/ES+VS+RR_n":"48.79/**49.13**","Ref":"44.73","Delta/%":"4.47/10.00%"},{"Name":"FEVER","ES":"72.80","VS":"88.90","ES+VS/ES+VS_n":"89.29/90.05","ES+RR/ES+RR_n":"84.38/84.94","VS+RR/VS+RR_n":"89.84/90.30","ES+VS+RR/ES+VS+RR_n":"90.21/**91.00**","Ref":"89.02","Delta/%":"2.10/2.36%"},{"Name":"FiQA2018","ES":"23.89","VS":"42.29","ES+VS/ES+VS_n":"42.57/42.79","ES+RR/ES+RR_n":"36.62/36.31","VS+RR/VS+RR_n":"43.04/43.09","ES+VS+RR/ES+VS+RR_n":"43.19/**43.22**","Ref":"42.4","Delta/%":"0.93/2.19%"},{"Name":"HotpotQA","ES":"54.94","VS":"73.65","ES+VS/ES+VS_n":"74.74/75.01","ES+RR/ES+RR_n":"74.93/75.39","VS+RR/VS+RR_n":"77.64/78.07","ES+VS+RR/ES+VS+RR_n":"77.95/**78.37**","Ref":"73.65","Delta/%":"4.72/6.40%"},{"Name":"MSMARCO","ES":"21.84","VS":"41.77","ES+VS/ES+VS_n":"41.65/41.72","ES+RR/ES+RR_n":"46.93/47.15","VS+RR/VS+RR_n":"47.11/**47.24**","ES+VS+RR/ES+VS+RR_n":"47.09/47.23","Ref":"41.77","Delta/%":"5.46/13.07%"},{"Name":"NFCorpus","ES":"31.40","VS":"36.74","ES+VS/ES+VS_n":"37.37/37.63","ES+RR/ES+RR_n":"34.51/35.36","VS+RR/VS+RR_n":"37.32/37.31","ES+VS+RR/ES+VS+RR_n":"**37.70**/37.15","Ref":"36.77","Delta/%":"0.41/1.11%"},{"Name":"NQ","ES":"27.21","VS":"61.33","ES+VS/ES+VS_n":"60.51/61.20","ES+RR/ES+RR_n":"55.60/55.47","VS+RR/VS+RR_n":"61.50/62.24","ES+VS+RR/ES+VS+RR_n":"62.27/**62.35**","Ref":"62.43","Delta/%":"1.02/1.66%"},{"Name":"QuoraRetrieval","ES":"74.23","VS":"80.73","ES+VS/ES+VS_n":"86.64/86.91","ES+RR/ES+RR_n":"84.14/84.40","VS+RR/VS+RR_n":"87.76/88.10","ES+VS+RR/ES+VS+RR_n":"88.39/**88.54**","Ref":"87.42","Delta/%":"7.81/9.67%"},{"Name":"SCIDOCS","ES":"14.68","VS":"21.03","ES+VS/ES+VS_n":"20.49/20.06","ES+RR/ES+RR_n":"16.48/16.48","VS+RR/VS+RR_n":"**20.51**/20.19","ES+VS+RR/ES+VS+RR_n":"20.34/20.03","Ref":"21.10","Delta/%":"-1.00/-4.75%"},{"Name":"SciFact","ES":"58.42","VS":"73.16","ES+VS/ES+VS_n":"73.28/75.08","ES+RR/ES+RR_n":"69.08/69.69","VS+RR/VS+RR_n":"72.73/73.62","ES+VS+RR/ES+VS+RR_n":"73.08/**75.33**","Ref":"73.55","Delta/%":"2.17/2.96%"},{"Name":"Touche2020","ES":"29.92","VS":"**32.65**","ES+VS/ES+VS_n":"31.86/34.26","ES+RR/ES+RR_n":"29.76/29.93","VS+RR/VS+RR_n":"30.47/29.30","ES+VS+RR/ES+VS+RR_n":"31.51/30.98","Ref":"31.47","Delta/%":"-1.67/-5.11%"},{"Name":"TRECCOVID","ES":"52.02","VS":"78.92","ES+VS/ES+VS_n":"77.78/79.12","ES+RR/ES+RR_n":"75.59/76.95","VS+RR/VS+RR_n":"80.34/81.19","ES+VS+RR/ES+VS+RR_n":"81.97/**83.01**","Ref":"79.65","Delta/%":"4.09/5.18%"},{"Name":"Average","ES":"38.32","VS":"54.24","ES+VS/ES+VS_n":"54.64/55.12","ES+RR/ES+RR_n":"51.28/51.62","VS+RR/VS+RR_n":"55.74/55.94","ES+VS+RR/ES+VS+RR_n":"56.15/**56.47**","Ref":"54.91","Delta/%":"2.23/4.11%"}]
diff --git a/www/content/docs/experiments/training.mdx b/www/content/docs/experiments/training.mdx
@@ -51,7 +51,9 @@ We first build an elasticsearch index, a vector index and a reranker using scifa
 
 The Denser retriever is illustrated in the following diagram, with the top and bottom boxes describing the training and inference respectively. For each query in the training data, we query elasticsearch and vector database to retrieve two sets of topk (100) passages respectively. We note that these two sets may overlap. We then apply a ML reranker to rerank the passages returned from elasticsearch and vector search.
 
- ![](./RAG-flow-data.png)
+import RagFlowData from './rag-flow-data.png'
+
+<ImageZoom src={RagFlowData} alt="Denser Retriever" className="border border-dashed rounded-md" />
 
 Let's consider a query and two passages in the following. The first passage is annotated with label 1 (relevant) while the second is 0 (irrelevant).
 

diff --git a/www/package.json b/www/package.json
@@ -24,6 +24,7 @@
     "react": "18.2.0",
     "react-dom": "18.2.0",
     "react-use": "^17.5.0",
+    "recharts": "^2.12.7",
     "sharp": "^0.33.4",
     "shiki": "1.2.1",
     "sst": "^3.0.13",
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		[{"Name":"ArguAna","ES":"42.93","VS":"56.49","ES+VS/ES+VS_n":"56.68/57.27","ES+RR/ES+RR_n":"47.45/48.21","VS+RR/VS+RR_n":"56.32/56.44","ES+VS+RR/ES+VS+RR_n":"56.81/57.28","Ref":"56.44","Delta/%":"0.79/1.39%"},{"Name":"ClimateFEVER","ES":"18.10","VS":"39.12","ES+VS/ES+VS_n":"39.21/39.01","ES+RR/ES+RR_n":"28.20/28.34","VS+RR/VS+RR_n":"39.06/38.71","ES+VS+RR/ES+VS+RR_n":"39.11/39.25","Ref":"39.37","Delta/%":"0.13/0.33%"},{"Name":"CQADupstack","ES":"25.13","VS":"42.23","ES+VS/ES+VS_n":"42.40/42.51","ES+RR/ES+RR_n":"37.68/37.54","VS+RR/VS+RR_n":"43.92/44.25","ES+VS+RR/ES+VS+RR_n":"43.85/44.32","Ref":"43.81","Delta/%":"2.09/4.94%"},{"Name":"DBPedia","ES":"27.42","VS":"44.66","ES+VS/ES+VS_n":"45.26/44.26","ES+RR/ES+RR_n":"47.94/48.26","VS+RR/VS+RR_n":"48.62/49.08","ES+VS+RR/ES+VS+RR_n":"48.79/49.13","Ref":"44.73","Delta/%":"4.47/10.00%"},{"Name":"FEVER","ES":"72.80","VS":"88.90","ES+VS/ES+VS_n":"89.29/90.05","ES+RR/ES+RR_n":"84.38/84.94","VS+RR/VS+RR_n":"89.84/90.30","ES+VS+RR/ES+VS+RR_n":"90.21/91.00","Ref":"89.02","Delta/%":"2.10/2.36%"},{"Name":"FiQA2018","ES":"23.89","VS":"42.29","ES+VS/ES+VS_n":"42.57/42.79","ES+RR/ES+RR_n":"36.62/36.31","VS+RR/VS+RR_n":"43.04/43.09","ES+VS+RR/ES+VS+RR_n":"43.19/43.22","Ref":"42.4","Delta/%":"0.93/2.19%"},{"Name":"HotpotQA","ES":"54.94","VS":"73.65","ES+VS/ES+VS_n":"74.74/75.01","ES+RR/ES+RR_n":"74.93/75.39","VS+RR/VS+RR_n":"77.64/78.07","ES+VS+RR/ES+VS+RR_n":"77.95/78.37","Ref":"73.65","Delta/%":"4.72/6.40%"},{"Name":"MSMARCO","ES":"21.84","VS":"41.77","ES+VS/ES+VS_n":"41.65/41.72","ES+RR/ES+RR_n":"46.93/47.15","VS+RR/VS+RR_n":"47.11/47.24","ES+VS+RR/ES+VS+RR_n":"47.09/47.23","Ref":"41.77","Delta/%":"5.46/13.07%"},{"Name":"NFCorpus","ES":"31.40","VS":"36.74","ES+VS/ES+VS_n":"37.37/37.63","ES+RR/ES+RR_n":"34.51/35.36","VS+RR/VS+RR_n":"37.32/37.31","ES+VS+RR/ES+VS+RR_n":"37.70/37.15","Ref":"36.77","Delta/%":"0.41/1.11%"},{"Name":"NQ","ES":"27.21","VS":"61.33","ES+VS/ES+VS_n":"60.51/61.20","ES+RR/ES+RR_n":"55.60/55.47","VS+RR/VS+RR_n":"61.50/62.24","ES+VS+RR/ES+VS+RR_n":"62.27/62.35","Ref":"62.43","Delta/%":"1.02/1.66%"},{"Name":"QuoraRetrieval","ES":"74.23","VS":"80.73","ES+VS/ES+VS_n":"86.64/86.91","ES+RR/ES+RR_n":"84.14/84.40","VS+RR/VS+RR_n":"87.76/88.10","ES+VS+RR/ES+VS+RR_n":"88.39/88.54","Ref":"87.42","Delta/%":"7.81/9.67%"},{"Name":"SCIDOCS","ES":"14.68","VS":"21.03","ES+VS/ES+VS_n":"20.49/20.06","ES+RR/ES+RR_n":"16.48/16.48","VS+RR/VS+RR_n":"20.51/20.19","ES+VS+RR/ES+VS+RR_n":"20.34/20.03","Ref":"21.10","Delta/%":"-1.00/-4.75%"},{"Name":"SciFact","ES":"58.42","VS":"73.16","ES+VS/ES+VS_n":"73.28/75.08","ES+RR/ES+RR_n":"69.08/69.69","VS+RR/VS+RR_n":"72.73/73.62","ES+VS+RR/ES+VS+RR_n":"73.08/75.33","Ref":"73.55","Delta/%":"2.17/2.96%"},{"Name":"Touche2020","ES":"29.92","VS":"32.65","ES+VS/ES+VS_n":"31.86/34.26","ES+RR/ES+RR_n":"29.76/29.93","VS+RR/VS+RR_n":"30.47/29.30","ES+VS+RR/ES+VS+RR_n":"31.51/30.98","Ref":"31.47","Delta/%":"-1.67/-5.11%"},{"Name":"TRECCOVID","ES":"52.02","VS":"78.92","ES+VS/ES+VS_n":"77.78/79.12","ES+RR/ES+RR_n":"75.59/76.95","VS+RR/VS+RR_n":"80.34/81.19","ES+VS+RR/ES+VS+RR_n":"81.97/83.01","Ref":"79.65","Delta/%":"4.09/5.18%"},{"Name":"Average","ES":"38.32","VS":"54.24","ES+VS/ES+VS_n":"54.64/55.12","ES+RR/ES+RR_n":"51.28/51.62","VS+RR/VS+RR_n":"55.74/55.94","ES+VS+RR/ES+VS+RR_n":"56.15/56.47","Ref":"54.91","Delta/%":"2.23/4.11%"}]