writinwaters
commited on
Commit
·
d30c752
1
Parent(s):
8aa5e9b
Updated faq.md (#636)
Browse files### What problem does this PR solve?
_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._
### Type of change
- [x] Documentation Update
- docs/faq.md +58 -13
docs/faq.md
CHANGED
|
@@ -193,18 +193,31 @@ docker logs -f ragflow-server
|
|
| 193 |
2. Check if the **task_executor.py** process exists.
|
| 194 |
3. Check if your RAGFlow server can access hf-mirror.com or huggingface.com.
|
| 195 |
|
|
|
|
| 196 |
|
| 197 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 198 |
|
| 199 |
An index failure usually indicates an unavailable Elasticsearch service.
|
| 200 |
|
| 201 |
-
#### 4.
|
| 202 |
|
| 203 |
```bash
|
| 204 |
tail -f path_to_ragflow/docker/ragflow-logs/rag/*.log
|
| 205 |
```
|
| 206 |
|
| 207 |
-
#### 4.
|
| 208 |
|
| 209 |
```bash
|
| 210 |
$ docker ps
|
|
@@ -218,7 +231,7 @@ d8c86f06c56b mysql:5.7.18 "docker-entrypoint.s…" 7 days ago Up
|
|
| 218 |
cd29bcb254bc quay.io/minio/minio:RELEASE.2023-12-20T01-00-02Z "/usr/bin/docker-ent…" 2 weeks ago Up 11 hours 0.0.0.0:9001->9001/tcp, :::9001->9001/tcp, 0.0.0.0:9000->9000/tcp, :::9000->9000/tcp ragflow-minio
|
| 219 |
```
|
| 220 |
|
| 221 |
-
#### 4.
|
| 222 |
|
| 223 |
1. Check the status of your Elasticsearch component:
|
| 224 |
|
|
@@ -245,23 +258,26 @@ $ docker ps
|
|
| 245 |
curl http://<IP_OF_ES>:<PORT_OF_ES>
|
| 246 |
```
|
| 247 |
|
|
|
|
| 248 |
|
| 249 |
-
|
|
|
|
|
|
|
| 250 |
|
| 251 |
Your IP address or port number may be incorrect. If you are using the default configurations, enter http://<IP_OF_YOUR_MACHINE> (**NOT 9380, AND NO PORT NUMBER REQUIRED!**) in your browser. This should work.
|
| 252 |
|
| 253 |
-
#### 4.
|
| 254 |
|
| 255 |
A correct Ollama IP address and port is crucial to adding models to Ollama:
|
| 256 |
|
| 257 |
- If you are on demo.ragflow.io, ensure that the server hosting Ollama has a publicly accessible IP address.Note that 127.0.0.1 is not a publicly accessible IP address.
|
| 258 |
- If you deploy RAGFlow locally, ensure that Ollama and RAGFlow are in the same LAN and can comunicate with each other.
|
| 259 |
|
| 260 |
-
#### 4.
|
| 261 |
|
| 262 |
Yes, we do. See the Python files under the **rag/app** folder.
|
| 263 |
|
| 264 |
-
#### 4.
|
| 265 |
|
| 266 |
You probably forgot to update the **MAX_CONTENT_LENGTH** environment variable:
|
| 267 |
|
|
@@ -280,7 +296,7 @@ docker compose up ragflow -d
|
|
| 280 |
```
|
| 281 |
*Now you should be able to upload files of sizes less than 100MB.*
|
| 282 |
|
| 283 |
-
#### 4.
|
| 284 |
|
| 285 |
This exception occurs when starting up the RAGFlow server. Try the following:
|
| 286 |
|
|
@@ -303,7 +319,7 @@ This exception occurs when starting up the RAGFlow server. Try the following:
|
|
| 303 |
docker compose up
|
| 304 |
```
|
| 305 |
|
| 306 |
-
#### 4.
|
| 307 |
|
| 308 |

|
| 309 |
|
|
@@ -311,6 +327,13 @@ This exception occurs when starting up the RAGFlow server. Try the following:
|
|
| 311 |
2. Do not forget to append **/v1/** to **http://IP:port**:
|
| 312 |
**http://IP:port/v1/**
|
| 313 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 314 |
|
| 315 |
## Usage
|
| 316 |
|
|
@@ -344,11 +367,11 @@ You can use Ollama to deploy local LLM. See [here](https://github.com/infiniflow
|
|
| 344 |
2. Right click the desired knowledge base to display the **Configuration** dialogue.
|
| 345 |
3. Choose **Q&A** as the chunk method and click **Save** to confirm your change.
|
| 346 |
|
| 347 |
-
### Do I need to connect to Redis?
|
| 348 |
|
| 349 |
No, connecting to Redis is not required.
|
| 350 |
|
| 351 |
-
### `Error: Range of input length should be [1, 30000]`
|
| 352 |
|
| 353 |
This error occurs because there are too many chunks matching your search criteria. Try reducing the **TopN** and increasing **Similarity threshold** to fix this issue:
|
| 354 |
|
|
@@ -357,4 +380,26 @@ This error occurs because there are too many chunks matching your search criteri
|
|
| 357 |
3. Reduce the **TopN** and/or raise **Silimarity threshold**.
|
| 358 |
4. Click **OK** to confirm your changes.
|
| 359 |
|
| 360 |
-

|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 193 |
2. Check if the **task_executor.py** process exists.
|
| 194 |
3. Check if your RAGFlow server can access hf-mirror.com or huggingface.com.
|
| 195 |
|
| 196 |
+
#### 4.5 Why does my pdf parsing stall near completion, while the log does not show any error?
|
| 197 |
|
| 198 |
+
If your RAGFlow is deployed *locally*, the parsing process is likely killed due to insufficient RAM. Try increasing your memory allocation by increasing the `MEM_LIMIT` value in **docker/.env**.
|
| 199 |
+
|
| 200 |
+
> Ensure that you restart up your RAGFlow server for your changes to take effect!
|
| 201 |
+
> ```bash
|
| 202 |
+
> docker compose stop
|
| 203 |
+
> ```
|
| 204 |
+
> ```bash
|
| 205 |
+
> docker compose up -d
|
| 206 |
+
> ```
|
| 207 |
+
|
| 208 |
+

|
| 209 |
+
|
| 210 |
+
#### 4.6 `Index failure`
|
| 211 |
|
| 212 |
An index failure usually indicates an unavailable Elasticsearch service.
|
| 213 |
|
| 214 |
+
#### 4.7 How to check the log of RAGFlow?
|
| 215 |
|
| 216 |
```bash
|
| 217 |
tail -f path_to_ragflow/docker/ragflow-logs/rag/*.log
|
| 218 |
```
|
| 219 |
|
| 220 |
+
#### 4.8 How to check the status of each component in RAGFlow?
|
| 221 |
|
| 222 |
```bash
|
| 223 |
$ docker ps
|
|
|
|
| 231 |
cd29bcb254bc quay.io/minio/minio:RELEASE.2023-12-20T01-00-02Z "/usr/bin/docker-ent…" 2 weeks ago Up 11 hours 0.0.0.0:9001->9001/tcp, :::9001->9001/tcp, 0.0.0.0:9000->9000/tcp, :::9000->9000/tcp ragflow-minio
|
| 232 |
```
|
| 233 |
|
| 234 |
+
#### 4.9 `Exception: Can't connect to ES cluster`
|
| 235 |
|
| 236 |
1. Check the status of your Elasticsearch component:
|
| 237 |
|
|
|
|
| 258 |
curl http://<IP_OF_ES>:<PORT_OF_ES>
|
| 259 |
```
|
| 260 |
|
| 261 |
+
#### 4.10 Can't start ES container and get `Elasticsearch did not exit normally`
|
| 262 |
|
| 263 |
+
This is because you forgot to update the `vm.max_map_count` value in **/etc/sysctl.conf** and your change to this value was reset after a system reboot.
|
| 264 |
+
|
| 265 |
+
#### 4.11 `{"data":null,"retcode":100,"retmsg":"<NotFound '404: Not Found'>"}`
|
| 266 |
|
| 267 |
Your IP address or port number may be incorrect. If you are using the default configurations, enter http://<IP_OF_YOUR_MACHINE> (**NOT 9380, AND NO PORT NUMBER REQUIRED!**) in your browser. This should work.
|
| 268 |
|
| 269 |
+
#### 4.12 `Ollama - Mistral instance running at 127.0.0.1:11434 but cannot add Ollama as model in RagFlow`
|
| 270 |
|
| 271 |
A correct Ollama IP address and port is crucial to adding models to Ollama:
|
| 272 |
|
| 273 |
- If you are on demo.ragflow.io, ensure that the server hosting Ollama has a publicly accessible IP address.Note that 127.0.0.1 is not a publicly accessible IP address.
|
| 274 |
- If you deploy RAGFlow locally, ensure that Ollama and RAGFlow are in the same LAN and can comunicate with each other.
|
| 275 |
|
| 276 |
+
#### 4.13 Do you offer examples of using deepdoc to parse PDF or other files?
|
| 277 |
|
| 278 |
Yes, we do. See the Python files under the **rag/app** folder.
|
| 279 |
|
| 280 |
+
#### 4.14 Why did I fail to upload a 10MB+ file to my locally deployed RAGFlow?
|
| 281 |
|
| 282 |
You probably forgot to update the **MAX_CONTENT_LENGTH** environment variable:
|
| 283 |
|
|
|
|
| 296 |
```
|
| 297 |
*Now you should be able to upload files of sizes less than 100MB.*
|
| 298 |
|
| 299 |
+
#### 4.15 `Table 'rag_flow.document' doesn't exist`
|
| 300 |
|
| 301 |
This exception occurs when starting up the RAGFlow server. Try the following:
|
| 302 |
|
|
|
|
| 319 |
docker compose up
|
| 320 |
```
|
| 321 |
|
| 322 |
+
#### 4.16 `hint : 102 Fail to access model Connection error`
|
| 323 |
|
| 324 |

|
| 325 |
|
|
|
|
| 327 |
2. Do not forget to append **/v1/** to **http://IP:port**:
|
| 328 |
**http://IP:port/v1/**
|
| 329 |
|
| 330 |
+
#### 4.17 `FileNotFoundError: [Errno 2] No such file or directory`
|
| 331 |
+
|
| 332 |
+
1. Check if the status of your minio container is healthy:
|
| 333 |
+
```bash
|
| 334 |
+
docker ps
|
| 335 |
+
```
|
| 336 |
+
2. Ensure that the username and password settings of MySQL and MinIO in **docker/.env** are in line with those in **docker/service_conf.yml**.
|
| 337 |
|
| 338 |
## Usage
|
| 339 |
|
|
|
|
| 367 |
2. Right click the desired knowledge base to display the **Configuration** dialogue.
|
| 368 |
3. Choose **Q&A** as the chunk method and click **Save** to confirm your change.
|
| 369 |
|
| 370 |
+
### 7 Do I need to connect to Redis?
|
| 371 |
|
| 372 |
No, connecting to Redis is not required.
|
| 373 |
|
| 374 |
+
### 8 `Error: Range of input length should be [1, 30000]`
|
| 375 |
|
| 376 |
This error occurs because there are too many chunks matching your search criteria. Try reducing the **TopN** and increasing **Similarity threshold** to fix this issue:
|
| 377 |
|
|
|
|
| 380 |
3. Reduce the **TopN** and/or raise **Silimarity threshold**.
|
| 381 |
4. Click **OK** to confirm your changes.
|
| 382 |
|
| 383 |
+

|
| 384 |
+
|
| 385 |
+
### 9 How to update RAGFlow to the latest version?
|
| 386 |
+
|
| 387 |
+
1. Pull the latest source code
|
| 388 |
+
```bash
|
| 389 |
+
cd ragflow
|
| 390 |
+
git pull
|
| 391 |
+
```
|
| 392 |
+
2. If you used `docker compose up -d` to start up RAGFlow server:
|
| 393 |
+
```bash
|
| 394 |
+
docker pull infiniflow/ragflow:dev
|
| 395 |
+
```
|
| 396 |
+
```bash
|
| 397 |
+
docker compose up ragflow -d
|
| 398 |
+
```
|
| 399 |
+
3. If you used `docker compose -f docker-compose-CN.yml up -d` to start up RAGFlow server:
|
| 400 |
+
```bash
|
| 401 |
+
docker pull swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:dev
|
| 402 |
+
```
|
| 403 |
+
```bash
|
| 404 |
+
docker compose -f docker-compose-CN.yml up -d
|
| 405 |
+
```
|