File size: 32,999 Bytes
e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d e090e58 4e0a78d 2d8207d 4e0a78d 2d8207d 4e0a78d 2d8207d 4e0a78d 2d8207d 4e0a78d 2d8207d 4e0a78d 2d8207d 4e0a78d 3b1b360 4e0a78d 3b1b360 4e0a78d 3b1b360 4e0a78d 3b1b360 4e0a78d 3b1b360 4e0a78d 3b1b360 4e0a78d 3b1b360 4e0a78d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 |
---
sidebar_position: 1
slug: /api
---
# API reference
RAGFlow offers RESTful APIs for you to integrate its capabilities into third-party applications.
## Base URL
```
https://demo.ragflow.io/v1/
```
## Authorization
All of RAGFlow's RESTFul APIs use API key for authorization, so keep it safe and do not expose it to the front end.
Put your API key in the request header.
```buildoutcfg
Authorization: Bearer {API_KEY}
```
To get your API key:
1. In RAGFlow, click **Chat** tab in the middle top of the page.
2. Hover over the corresponding dialogue **>** **Chat Bot API** to show the chatbot API configuration page.
3. Click **Api Key** **>** **Create new key** to create your API key.
4. Copy and keep your API key safe.
## Create conversation
This method creates (news) a conversation for a specific user.
### Request
#### Request URI
| Method | Request URI |
|----------|-------------------------------------------------------------|
| GET | `/api/new_conversation` |
:::note
You are *required* to save the `data.id` value returned in the response data, which is the session ID for all upcoming conversations.
:::
#### Request parameter
| Name | Type | Required | Description |
|----------|--------|----------|-------------------------------------------------------------|
| `user_id`| string | Yes | The unique identifier assigned to each user. `user_id` must be less than 32 characters and cannot be empty. The following character sets are supported: <br />- 26 lowercase English letters (a-z)<br />- 26 uppercase English letters (A-Z)<br />- 10 digits (0-9)<br />- "_", "-", "." |
### Response
<details>
<summary>Response example</summary>
<pre><code>
{
"data": {
"create_date": "Fri, 12 Apr 2024 17:26:21 GMT",
"create_time": 1712913981857,
"dialog_id": "4f0a2e4cb9af11ee9ba20aef05f5e94f",
"duration": 0.0,
"id": "b9b2e098f8ae11ee9f45fa163e197198",
"message": [
{
"content": "Hi, I'm your assistant, what can I do for you?",
"role": "assistant"
}
],
"reference": [],
"tokens": 0,
"update_date": "Fri, 12 Apr 2024 17:26:21 GMT",
"update_time": 1712913981857,
"user_id": "<USER_ID_SET_BY_THE_CALLER>"
},
"retcode": 0,
"retmsg": "success"
}
</code></pre>
</details>
## Get conversation history
This method retrieves the history of a specified conversation session.
### Request
#### Request URI
| Method | Request URI |
|----------|-------------------------------------------------------------|
| GET | `/api/conversation/<id>` |
### Request parameter
| Name | Type | Required | Description |
|----------|--------|----------|-------------------------------------------------------------|
| `id` | string | Yes | The unique identifier assigned to a conversation session. `id` must be less than 32 characters and cannot be empty. The following character sets are supported: <br />- 26 lowercase English letters (a-z)<br />- 26 uppercase English letters (A-Z)<br />- 10 digits (0-9)<br />- "_", "-", "." |
### Response
#### Response parameter
- `message`: All conversations in the specified conversation session.
- `role`: `"user"` or `"assistant"`.
- `content`: The text content of user or assistant. The citations are in a format like `##0$$`. The number in the middle, 0 in this case, indicates which part in data.reference.chunks it refers to.
- `user_id`: This is set by the caller.
- `reference`: Each reference corresponds to one of the assistant's answers in `data.message`.
- `chunks`
- `content_with_weight`: Content of the chunk.
- `doc_name`: Name of the *hit* document.
- `img_id`: The image ID of the chunk. It is an optional field only for PDF, PPTX, and images. Call ['GET' /document/get/<id>](#get-document-content-or-image) to retrieve the image.
- positions: [page_number, [upleft corner(x, y)], [right bottom(x, y)]], the chunk position, only for PDF.
- similarity: The hybrid similarity.
- term_similarity: The keyword simimlarity.
- vector_similarity: The embedding similarity.
- `doc_aggs`:
- `doc_id`: ID of the *hit* document. Call ['GET' /document/get/<id>](#get-document-content-or-image) to retrieve the document.
- `doc_name`: Name of the *hit* document.
- `count`: The number of *hit* chunks in this document.
<details>
<summary>Response example</summary>
<pre><code>
{
"data": {
"create_date": "Mon, 01 Apr 2024 09:28:42 GMT",
"create_time": 1711934922220,
"dialog_id": "df4a4916d7bd11eeaa650242ac180006",
"id": "2cae30fcefc711ee94140242ac180006",
"message": [
{
"content": "Hi! I'm your assistant, what can I do for you?",
"role": "assistant"
},
{
"content": "What's the vit score for GPT-4?",
"role": "user"
},
{
"content": "The ViT Score for GPT-4 in the zero-shot scenario is 0.5058, and in the few-shot scenario, it is 0.6480. ##0$$",
"role": "assistant"
},
{
"content": "How is the nvlink topology like?",
"role": "user"
},
{
"content": "NVLink topology refers to the arrangement of connections between GPUs using NVIDIA's NVLink technology. Correct NVLink topology for NVIDIA A100 cards involves connecting one GPU to another through a series of NVLink bridges ##0$$. Each of the three attached bridges spans two PCIe slots, and for optimal performance and balanced bridge topology, all three NVLink bridges should be used when connecting two adjacent A100 cards.\n\nHere's a summary of the correct and incorrect topologies:\n\n- **Correct**: Both GPUs are connected via all three NVLink bridges, ensuring full bandwidth and proper communication.\n- **Incorrect**: Not using all three bridges or having an uneven connection configuration would result in suboptimal performance.\n\nIt's also important to note that for multi-CPU systems, both A100 cards in a bridged pair should be within the same CPU domain, unless each CPU has a single A100 PCIe card, in which case they can be bridged together.",
"role": "assistant"
}
],
"user_id": "<USER_ID_SET_BY_THE_CALLER>",
"reference": [
{
"chunks": [
{
"chunk_id": "d0bc7892c3ec4aeac071544fd56730a8",
"content_ltks": "tabl 1:openagi task-solv perform under differ set for three closed-sourc llm . boldfac denot the highest score under each learn schema . metric gpt-3.5-turbo claude-2 gpt-4 zero few zero few zero few clip score 0.0 0.0 0.0 0.2543 0.0 0.3055 bert score 0.1914 0.3820 0.2111 0.5038 0.2076 0.6307 vit score 0.2437 0.7497 0.4082 0.5416 0.5058 0.6480 overal 0.1450 0.3772 0.2064 0.4332 0.2378 0.5281",
"content_with_weight": "<table><caption>Table 1: OpenAGI task-solving performances under different settings for three closed-source LLMs. Boldface denotes the highest score under each learning schema.</caption>\n<tr><th rowspan=2 >Metrics</th><th >GPT-3.5-turbo</th><th></th><th >Claude-2</th><th >GPT-4</th></tr>\n<tr><th >Zero</th><th >Few</th><th >Zero Few</th><th >Zero Few</th></tr>\n<tr><td >CLIP Score</td><td >0.0</td><td >0.0</td><td >0.0 0.2543</td><td >0.0 0.3055</td></tr>\n<tr><td >BERT Score</td><td >0.1914</td><td >0.3820</td><td >0.2111 0.5038</td><td >0.2076 0.6307</td></tr>\n<tr><td >ViT Score</td><td >0.2437</td><td >0.7497</td><td >0.4082 0.5416</td><td >0.5058 0.6480</td></tr>\n<tr><td >Overall</td><td >0.1450</td><td >0.3772</td><td >0.2064 0.4332</td><td >0.2378 0.5281</td></tr>\n</table>",
"doc_id": "c790da40ea8911ee928e0242ac180005",
"doc_name": "OpenAGI When LLM Meets Domain Experts.pdf",
"img_id": "afab9fdad6e511eebdb20242ac180006-d0bc7892c3ec4aeac071544fd56730a8",
"important_kwd": [],
"kb_id": "afab9fdad6e511eebdb20242ac180006",
"positions": [
[
9.0,
159.9383341471354,
472.1773274739583,
223.58013916015625,
307.86692301432294
]
],
"similarity": 0.7310340654129031,
"term_similarity": 0.7671974387781668,
"vector_similarity": 0.40556370512552886
},
{
"chunk_id": "7e2345d440383b756670e1b0f43a7007",
"content_ltks": "5.5 experiment analysi the main experiment result are tabul in tab . 1 and 2 , showcas the result for closed-sourc and open-sourc llm , respect . the overal perform is calcul a the averag of cllp 8 bert and vit score . here , onli the task descript of the benchmark task are fed into llm(addit inform , such a the input prompt and llm\u2019output , is provid in fig . a.4 and a.5 in supplementari). broadli speak , closed-sourc llm demonstr superior perform on openagi task , with gpt-4 lead the pack under both zero-and few-shot scenario . in the open-sourc categori , llama-2-13b take the lead , consist post top result across variou learn schema--the perform possibl influenc by it larger model size . notabl , open-sourc llm significantli benefit from the tune method , particularli fine-tun and\u2019rltf . these method mark notic enhanc for flan-t5-larg , vicuna-7b , and llama-2-13b when compar with zero-shot and few-shot learn schema . in fact , each of these open-sourc model hit it pinnacl under the rltf approach . conclus , with rltf tune , the perform of llama-2-13b approach that of gpt-3.5 , illustr it potenti .",
"content_with_weight": "5.5 Experimental Analysis\nThe main experimental results are tabulated in Tab. 1 and 2, showcasing the results for closed-source and open-source LLMs, respectively. The overall performance is calculated as the average of CLlP\n8\nBERT and ViT scores. Here, only the task descriptions of the benchmark tasks are fed into LLMs (additional information, such as the input prompt and LLMs\u2019 outputs, is provided in Fig. A.4 and A.5 in supplementary). Broadly speaking, closed-source LLMs demonstrate superior performance on OpenAGI tasks, with GPT-4 leading the pack under both zero- and few-shot scenarios. In the open-source category, LLaMA-2-13B takes the lead, consistently posting top results across various learning schema--the performance possibly influenced by its larger model size. Notably, open-source LLMs significantly benefit from the tuning methods, particularly Fine-tuning and\u2019 RLTF. These methods mark noticeable enhancements for Flan-T5-Large, Vicuna-7B, and LLaMA-2-13B when compared with zero-shot and few-shot learning schema. In fact, each of these open-source models hits its pinnacle under the RLTF approach. Conclusively, with RLTF tuning, the performance of LLaMA-2-13B approaches that of GPT-3.5, illustrating its potential.",
"doc_id": "c790da40ea8911ee928e0242ac180005",
"doc_name": "OpenAGI When LLM Meets Domain Experts.pdf",
"img_id": "afab9fdad6e511eebdb20242ac180006-7e2345d440383b756670e1b0f43a7007",
"important_kwd": [],
"kb_id": "afab9fdad6e511eebdb20242ac180006",
"positions": [
[
8.0,
107.3,
508.90000000000003,
686.3,
697.0
],
],
"similarity": 0.6691508616357027,
"term_similarity": 0.6999011754270821,
"vector_similarity": 0.39239803751328806
},
],
"doc_aggs": [
{
"count": 8,
"doc_id": "c790da40ea8911ee928e0242ac180005",
"doc_name": "OpenAGI When LLM Meets Domain Experts.pdf"
}
],
"total": 8
},
{
"chunks": [
{
"chunk_id": "8c11a1edddb21ad2ae0c43b4a5dcfa62",
"content_ltks": "nvlink bridg support nvidia\u00aenvlink\u00aei a high-spe point-to-point peer transfer connect , where one gpu can transfer data to and receiv data from one other gpu . the nvidia a100 card support nvlink bridg connect with a singl adjac a100 card . each of the three attach bridg span two pcie slot . to function correctli a well a to provid peak bridg bandwidth , bridg connect with an adjac a100 card must incorpor all three nvlink bridg . wherev an adjac pair of a100 card exist in the server , for best bridg perform and balanc bridg topolog , the a100 pair should be bridg . figur 4 illustr correct and incorrect a100 nvlink connect topolog . nvlink topolog\u2013top view figur 4. correct incorrect correct incorrect for system that featur multipl cpu , both a100 card of a bridg card pair should be within the same cpu domain\u2014that is , under the same cpu\u2019s topolog . ensur thi benefit workload applic perform . the onli except is for dual cpu system wherein each cpu ha a singl a100 pcie card under it;in that case , the two a100 pcie card in the system may be bridg togeth . a100 nvlink speed and bandwidth are given in the follow tabl . tabl 5. a100 nvlink speed and bandwidth paramet valu total nvlink bridg support by nvidia a100 3 total nvlink rx and tx lane support 96 data rate per nvidia a100 nvlink lane(each direct)50 gbp total maximum nvlink bandwidth 600 gbyte per second pb-10137-001_v03|8 nvidia a100 40gb pcie gpu acceler",
"content_with_weight": "NVLink Bridge Support\nNVIDIA\u00aeNVLink\u00aeis a high-speed point-to-point peer transfer connection, where one GPU can transfer data to and receive data from one other GPU. The NVIDIA A100 card supports NVLink bridge connection with a single adjacent A100 card.\nEach of the three attached bridges spans two PCIe slots. To function correctly as well as to provide peak bridge bandwidth, bridge connection with an adjacent A100 card must incorporate all three NVLink bridges. Wherever an adjacent pair of A100 cards exists in the server, for best bridging performance and balanced bridge topology, the A100 pair should be bridged. Figure 4 illustrates correct and incorrect A100 NVLink connection topologies.\nNVLink Topology \u2013Top Views \nFigure 4. \nCORRECT \nINCORRECT \nCORRECT \nINCORRECT \nFor systems that feature multiple CPUs, both A100 cards of a bridged card pair should be within the same CPU domain\u2014that is, under the same CPU\u2019s topology. Ensuring this benefits workload application performance. The only exception is for dual CPU systems wherein each CPU has a single A100 PCIe card under it; in that case, the two A100 PCIe cards in the system may be bridged together.\nA100 NVLink speed and bandwidth are given in the following table.\n<table><caption>Table 5. A100 NVLink Speed and Bandwidth </caption>\n<tr><th >Parameter </th><th >Value </th></tr>\n<tr><td >Total NVLink bridges supported by NVIDIA A100 </td><td >3 </td></tr>\n<tr><td >Total NVLink Rx and Tx lanes supported </td><td >96 </td></tr>\n<tr><td >Data rate per NVIDIA A100 NVLink lane (each direction)</td><td >50 Gbps </td></tr>\n<tr><td >Total maximum NVLink bandwidth</td><td >600 Gbytes per second </td></tr>\n</table>\nPB-10137-001_v03 |8\nNVIDIA A100 40GB PCIe GPU Accelerator",
"doc_id": "806d1ed0ea9311ee860a0242ac180005",
"doc_name": "A100-PCIE-Prduct-Brief.pdf",
"img_id": "afab9fdad6e511eebdb20242ac180006-8c11a1edddb21ad2ae0c43b4a5dcfa62",
"important_kwd": [],
"kb_id": "afab9fdad6e511eebdb20242ac180006",
"positions": [
[
12.0,
84.0,
541.3,
76.7,
96.7
],
],
"similarity": 0.3200748779905588,
"term_similarity": 0.3082244010114718,
"vector_similarity": 0.42672917080234146
},
],
"doc_aggs": [
{
"count": 1,
"doc_id": "806d1ed0ea9311ee860a0242ac180005",
"doc_name": "A100-PCIE-Prduct-Brief.pdf"
}
],
"total": 3
}
],
"update_date": "Tue, 02 Apr 2024 09:07:49 GMT",
"update_time": 1712020069421
},
"retcode": 0,
"retmsg": "success"
}
</code></pre>
</details>
## Get answer
This method retrieves from RAGFlow the answer to the user's latest question.
### Request
#### Request URI
| Method | Request URI |
|----------|-------------------------------------------------------------|
| POST | `/api/completion` |
### Request parameter
| Name | Type | Required | Description |
|------------------|--------|----------|---------------|
| `conversation_id`| string | Yes | The ID of the conversation session. Call ['GET' /new_conversation](#create-conversation) to retrieve the ID.|
| `messages` | json | Yes | The latest question in a JSON form, such as `[{"role": "user", "content": "How are you doing!"}]`|
| `quote` | bool | No | Default: true |
| `stream` | bool | No | Default: true |
| `doc_ids` | string | No | Document IDs delimited by comma, like `c790da40ea8911ee928e0242ac180005,23dsf34ree928e0242ac180005`. The retrieved contents will be confined to these documents. |
### Response
- `answer`: The answer to the user's latest question.
- `reference`:
- `chunks`: The retrieved chunks that contribute to the answer.
- `content_with_weight`: Content of the chunk.
- `doc_name`: Name of the *hit* document.
- `img_id`: The image ID of the chunk. It is an optional field only for PDF, PPTX, and images. Call ['GET' /document/get/<id>](#get-document-content-or-image) to retrieve the image.
- `positions`: [page_number, [upleft corner(x, y)], [right bottom(x, y)]], the chunk position, only for PDF.
- `similarity`: The hybrid similarity.
- `term_similarity`: The keyword simimlarity.
- `vector_similarity`: The embedding similarity.
- `doc_aggs`:
- `doc_id`: ID of the *hit* document. Call ['GET' /document/get/<id>](#get-document-content-or-image) to retrieve the document.
- `doc_name`: Name of the *hit* document.
- `count`: The number of *hit* chunks in this document.
<details>
<summary>Response example</summary>
<pre><code>
{
"data": {
"answer": "The ViT Score for GPT-4 in the zero-shot scenario is 0.5058, and in the few-shot scenario, it is 0.6480. ##0$$",
"reference": {
"chunks": [
{
"chunk_id": "d0bc7892c3ec4aeac071544fd56730a8",
"content_ltks": "tabl 1:openagi task-solv perform under differ set for three closed-sourc llm . boldfac denot the highest score under each learn schema . metric gpt-3.5-turbo claude-2 gpt-4 zero few zero few zero few clip score 0.0 0.0 0.0 0.2543 0.0 0.3055 bert score 0.1914 0.3820 0.2111 0.5038 0.2076 0.6307 vit score 0.2437 0.7497 0.4082 0.5416 0.5058 0.6480 overal 0.1450 0.3772 0.2064 0.4332 0.2378 0.5281",
"content_with_weight": "<table><caption>Table 1: OpenAGI task-solving performances under different settings for three closed-source LLMs. Boldface denotes the highest score under each learning schema.</caption>\n<tr><th rowspan=2 >Metrics</th><th >GPT-3.5-turbo</th><th></th><th >Claude-2</th><th >GPT-4</th></tr>\n<tr><th >Zero</th><th >Few</th><th >Zero Few</th><th >Zero Few</th></tr>\n<tr><td >CLIP Score</td><td >0.0</td><td >0.0</td><td >0.0 0.2543</td><td >0.0 0.3055</td></tr>\n<tr><td >BERT Score</td><td >0.1914</td><td >0.3820</td><td >0.2111 0.5038</td><td >0.2076 0.6307</td></tr>\n<tr><td >ViT Score</td><td >0.2437</td><td >0.7497</td><td >0.4082 0.5416</td><td >0.5058 0.6480</td></tr>\n<tr><td >Overall</td><td >0.1450</td><td >0.3772</td><td >0.2064 0.4332</td><td >0.2378 0.5281</td></tr>\n</table>",
"doc_id": "c790da40ea8911ee928e0242ac180005",
"doc_name": "OpenAGI When LLM Meets Domain Experts.pdf",
"img_id": "afab9fdad6e511eebdb20242ac180006-d0bc7892c3ec4aeac071544fd56730a8",
"important_kwd": [],
"kb_id": "afab9fdad6e511eebdb20242ac180006",
"positions": [
[
9.0,
159.9383341471354,
472.1773274739583,
223.58013916015625,
307.86692301432294
]
],
"similarity": 0.7310340654129031,
"term_similarity": 0.7671974387781668,
"vector_similarity": 0.40556370512552886
},
{
"chunk_id": "7e2345d440383b756670e1b0f43a7007",
"content_ltks": "5.5 experiment analysi the main experiment result are tabul in tab . 1 and 2 , showcas the result for closed-sourc and open-sourc llm , respect . the overal perform is calcul a the averag of cllp 8 bert and vit score . here , onli the task descript of the benchmark task are fed into llm(addit inform , such a the input prompt and llm\u2019output , is provid in fig . a.4 and a.5 in supplementari). broadli speak , closed-sourc llm demonstr superior perform on openagi task , with gpt-4 lead the pack under both zero-and few-shot scenario . in the open-sourc categori , llama-2-13b take the lead , consist post top result across variou learn schema--the perform possibl influenc by it larger model size . notabl , open-sourc llm significantli benefit from the tune method , particularli fine-tun and\u2019rltf . these method mark notic enhanc for flan-t5-larg , vicuna-7b , and llama-2-13b when compar with zero-shot and few-shot learn schema . in fact , each of these open-sourc model hit it pinnacl under the rltf approach . conclus , with rltf tune , the perform of llama-2-13b approach that of gpt-3.5 , illustr it potenti .",
"content_with_weight": "5.5 Experimental Analysis\nThe main experimental results are tabulated in Tab. 1 and 2, showcasing the results for closed-source and open-source LLMs, respectively. The overall performance is calculated as the average of CLlP\n8\nBERT and ViT scores. Here, only the task descriptions of the benchmark tasks are fed into LLMs (additional information, such as the input prompt and LLMs\u2019 outputs, is provided in Fig. A.4 and A.5 in supplementary). Broadly speaking, closed-source LLMs demonstrate superior performance on OpenAGI tasks, with GPT-4 leading the pack under both zero- and few-shot scenarios. In the open-source category, LLaMA-2-13B takes the lead, consistently posting top results across various learning schema--the performance possibly influenced by its larger model size. Notably, open-source LLMs significantly benefit from the tuning methods, particularly Fine-tuning and\u2019 RLTF. These methods mark noticeable enhancements for Flan-T5-Large, Vicuna-7B, and LLaMA-2-13B when compared with zero-shot and few-shot learning schema. In fact, each of these open-source models hits its pinnacle under the RLTF approach. Conclusively, with RLTF tuning, the performance of LLaMA-2-13B approaches that of GPT-3.5, illustrating its potential.",
"doc_id": "c790da40ea8911ee928e0242ac180005",
"doc_name": "OpenAGI When LLM Meets Domain Experts.pdf",
"img_id": "afab9fdad6e511eebdb20242ac180006-7e2345d440383b756670e1b0f43a7007",
"important_kwd": [],
"kb_id": "afab9fdad6e511eebdb20242ac180006",
"positions": [
[
8.0,
107.3,
508.90000000000003,
686.3,
697.0
]
],
"similarity": 0.6691508616357027,
"term_similarity": 0.6999011754270821,
"vector_similarity": 0.39239803751328806
}
],
"doc_aggs": {
"OpenAGI When LLM Meets Domain Experts.pdf": 4
},
"total": 8
}
},
"retcode": 0,
"retmsg": "success"
}
</code></pre>
</details>
## Get document content or image
This method retrieves the content or a specific image in a document. Used if you intend to display the content of a citation.
### Request
#### Request URI
| Method | Request URI |
|----------|-------------------------------------------------------------|
| GET | `/api/document/get/<id>` |
### Response
## Upload file
This method uploads a specific file to a specified knowledge base.
### Request
#### Request URI
| Method | Request URI |
|----------|-------------------------------------------------------------|
| POST | `/api/document/upload` |
### Response parameter
| Name | Type | Required | Description |
|-------------|--------|----------|---------------------------------------------------------|
| `file` | file | Yes | The file to upload. |
| `kb_name` | string | Yes | The name of the knowledge base to upload the file to. |
| `parser_id` | string | No | The parsing method (chunk template) to use. <br />- "naive": General;<br />- "qa": Q&A;<br />- "manual": Manual;<br />- "table": Table;<br />- "paper": Paper;<br />- "laws": Laws;<br />- "presentation": Presentation;<br />- "picture": Picture;<br />- "one": One. |
| `run` | string | No | 1: Automatically start file parsing. If `parser_id` is not set, RAGFlow uses the general template by default. |
### Response
<details>
<summary>Response example</summary>
<pre><code>
{
"data": {
"chunk_num": 0,
"create_date": "Thu, 25 Apr 2024 14:30:06 GMT",
"create_time": 1714026606921,
"created_by": "553ec818fd5711ee8ea63043d7ed348e",
"id": "41e9324602cd11ef9f5f3043d7ed348e",
"kb_id": "06802686c0a311ee85d6246e9694c130",
"location": "readme.txt",
"name": "readme.txt",
"parser_config": {
"field_map": {
},
"pages": [
[
0,
1000000
]
]
},
"parser_id": "general",
"process_begin_at": null,
"process_duation": 0.0,
"progress": 0.0,
"progress_msg": "",
"run": "0",
"size": 929,
"source_type": "local",
"status": "1",
"thumbnail": null,
"token_num": 0,
"type": "doc",
"update_date": "Thu, 25 Apr 2024 14:30:06 GMT",
"update_time": 1714026606921
},
"retcode": 0,
"retmsg": "success"
}
</code></pre>
</details>
## Get document chunks
This method retrieves the chunks of a specific document by `doc_name` or `doc_id`.
### Request
#### Request URI
| Method | Request URI |
|----------|-------------------------------------------------------------|
| GET | `/api/list_chunks` |
#### Request parameter
| Name | Type | Required | Description |
|------------|--------|----------|---------------------------------------------------------------------------------------------|
| `doc_name` | string | No | The name of the document in the knowledge base. It must not be empty if `doc_id` is not set.|
| `doc_id` | string | No | The ID of the document in the knowledge base. It must not be empty if `doc_name` is not set.|
### Response
<details>
<summary>Response example</summary>
<pre><code>
{
"data": [
{
"content": "Figure 14: Per-request neural-net processingof RL-Cache.\n103\n(sn)\nCPU\n 102\nGPU\n8101\n100\n8\n16 64 256 1K\n4K",
"doc_name": "RL-Cache.pdf",
"img_id": "0335167613f011ef91240242ac120006-b46c3524952f82dbe061ce9b123f2211"
},
{
"content": "4.3 ProcessingOverheadof RL-CacheACKNOWLEDGMENTSThis section evaluates how effectively our RL-Cache implemen-tation leverages modern multi-core CPUs and GPUs to keep the per-request neural-net processing overhead low. Figure 14 depictsThis researchwas supported inpart by the Regional Government of Madrid (grant P2018/TCS-4499, EdgeData-CM)andU.S. National Science Foundation (grants CNS-1763617 andCNS-1717179).REFERENCES",
"doc_name": "RL-Cache.pdf",
"img_id": "0335167613f011ef91240242ac120006-d4c12c43938eb55d2d8278eea0d7e6d7"
}
],
"retcode": 0,
"retmsg": "success"
}
</code></pre>
</details>
## Get document list
This method retrieves a list of documents from a specified knowledge base.
### Request
#### Request URI
| Method | Request URI |
|----------|-------------------------------------------------------------|
| POST | `/api/list_kb_docs` |
#### Request parameter
| Name | Type | Required | Description |
|-------------|--------|----------|-----------------------------------------------------------------------|
| `kb_name` | string | Yes | The name of the knowledge base, from which you get the document list. |
| `page` | int | No | The number of pages, default:1. |
| `page_size` | int | No | The number of docs for each page, default:15. |
| `orderby` | string | No | `chunk_num`, `create_time`, or `size`, default:`create_time` |
| `desc` | bool | No | Default:True. |
| `keywords` | string | No | Keyword of the document name. |
### Response
<details>
<summary>Response example</summary>
<pre><code>
{
"data": {
"docs": [
{
"doc_id": "bad89a84168c11ef9ce40242ac120006",
"doc_name": "test.xlsx"
},
{
"doc_id": "641a9b4013f111efb53f0242ac120006",
"doc_name": "1111.pdf"
}
],
"total": 2
},
"retcode": 0,
"retmsg": "success"
}
</code></pre>
</details>
## Delete documents
This method deletes documents by document ID or name.
### Request
#### Request URI
| Method | Request URI |
|----------|-------------------------------------------------------------|
| DELETE | `/api/document` |
#### Request parameter
| Name | Type | Required | Description |
|-------------|--------|----------|----------------------------|
| `doc_names` | List | No | A list of document names. It must not be empty if `doc_ids` is not set. |
| `doc_ids` | List | No | A list of document IDs. It must not be empty if `doc_names` is not set. |
### Response
<details>
<summary>Response example</summary>
<pre><code>
{
"data": true,
"retcode": 0,
"retmsg": "success"
}
</code></pre>
</details>
|