ragflow icon indicating copy to clipboard operation
ragflow copied to clipboard

[Question]: Can not parsing files using local Ollama embedding models

Open kkrusher opened this issue 1 year ago • 3 comments

Describe your problem

I installed Ollama locally and set up Ragflow using Docker. I downloaded the Qwen2 7b model and two different embedding models through Ollama. Then I created a knowledge base, config embedding model to be the one in Ollama, and uploaded files, but they couldn't be parsed. What could be the issue, and how can I resolve it?

Screenshot from 2024-08-22 22-32-30 Screenshot from 2024-08-22 22-34-37

kkrusher avatar Aug 22 '24 14:08 kkrusher

Does this error matters? Screenshot from 2024-08-22 22-45-02

kkrusher avatar Aug 22 '24 14:08 kkrusher

I guess some process of ragflow did not execute well. Could you paste the log by removing -d for docker compose?

KevinHuSh avatar Aug 23 '24 02:08 KevinHuSh

The following is log:

~/Documents/git_repos/ragflow/docker$ docker compose up WARN[0000] The "MACOS" variable is not set. Defaulting to a blank string. [+] Running 6/6 ✔ Network docker_ragflow Created 0.0s ✔ Container ragflow-mysql Created 0.1s ✔ Container ragflow-redis Created 0.1s ✔ Container ragflow-minio Created 0.1s ✔ Container ragflow-es-01 Created 0.1s ✔ Container ragflow-server Created 0.1s Attaching to ragflow-es-01, ragflow-minio, ragflow-mysql, ragflow-redis, ragflow-server ragflow-redis | 1:C 23 Aug 2024 10:19:10.959 * oO0OoO0OoO0Oo Redis is starting oO0OoO0OoO0Oo ragflow-redis | 1:C 23 Aug 2024 10:19:10.959 * Redis version=7.2.4, bits=64, commit=00000000, modified=0, pid=1, just started ragflow-redis | 1:C 23 Aug 2024 10:19:10.959 * Configuration loaded ragflow-redis | 1:M 23 Aug 2024 10:19:10.960 * monotonic clock: POSIX clock_gettime ragflow-redis | 1:M 23 Aug 2024 10:19:10.960 * Running mode=standalone, port=6379. ragflow-redis | 1:M 23 Aug 2024 10:19:10.960 * Server initialized ragflow-redis | 1:M 23 Aug 2024 10:19:10.960 * Loading RDB produced by version 7.2.4 ragflow-redis | 1:M 23 Aug 2024 10:19:10.960 * RDB age 21 seconds ragflow-redis | 1:M 23 Aug 2024 10:19:10.960 * RDB memory usage when created 0.97 Mb ragflow-redis | 1:M 23 Aug 2024 10:19:10.960 * Done loading RDB, keys loaded: 0, keys expired: 0. ragflow-redis | 1:M 23 Aug 2024 10:19:10.961 * DB loaded from disk: 0.000 seconds ragflow-redis | 1:M 23 Aug 2024 10:19:10.961 * Ready to accept connections tcp ragflow-minio | MinIO Object Storage Server ragflow-minio | Copyright: 2015-2023 MinIO, Inc. ragflow-minio | License: GNU AGPLv3 https://www.gnu.org/licenses/agpl-3.0.html ragflow-minio | Version: RELEASE.2023-12-20T01-00-02Z (go1.21.5 linux/amd64) ragflow-minio | ragflow-minio | Status: 1 Online, 0 Offline. ragflow-minio | S3-API: http://172.18.0.4:9000 http://127.0.0.1:9000
ragflow-minio | Console: http://172.18.0.4:9001 http://127.0.0.1:9001
ragflow-minio | ragflow-minio | Documentation: https://min.io/docs/minio/linux/index.html ragflow-minio | Warning: The standard parity is set to 0. This can lead to data loss. ragflow-mysql | 2024-08-23T10:19:11.142918Z 0 [Warning] TIMESTAMP with implicit DEFAULT value is deprecated. Please use --explicit_defaults_for_timestamp server option (see documentation for more details). ragflow-mysql | 2024-08-23T10:19:11.143580Z 0 [Note] mysqld (mysqld 5.7.18) starting as process 1 ... ragflow-mysql | 2024-08-23T10:19:11.146013Z 0 [Note] InnoDB: PUNCH HOLE support available ragflow-mysql | 2024-08-23T10:19:11.146071Z 0 [Note] InnoDB: Mutexes and rw_locks use GCC atomic builtins ragflow-mysql | 2024-08-23T10:19:11.146084Z 0 [Note] InnoDB: Uses event mutexes ragflow-mysql | 2024-08-23T10:19:11.146093Z 0 [Note] InnoDB: GCC builtin __atomic_thread_fence() is used for memory barrier ragflow-mysql | 2024-08-23T10:19:11.146118Z 0 [Note] InnoDB: Compressed tables use zlib 1.2.3 ragflow-mysql | 2024-08-23T10:19:11.146125Z 0 [Note] InnoDB: Using Linux native AIO ragflow-mysql | 2024-08-23T10:19:11.146723Z 0 [Note] InnoDB: Number of pools: 1 ragflow-mysql | 2024-08-23T10:19:11.146827Z 0 [Note] InnoDB: Using CPU crc32 instructions ragflow-mysql | 2024-08-23T10:19:11.148866Z 0 [Note] InnoDB: Initializing buffer pool, total size = 128M, instances = 1, chunk size = 128M ragflow-mysql | 2024-08-23T10:19:11.154151Z 0 [Note] InnoDB: Completed initialization of buffer pool ragflow-mysql | 2024-08-23T10:19:11.155544Z 0 [Note] InnoDB: If the mysqld execution user is authorized, page cleaner thread priority can be changed. See the man page of setpriority(). ragflow-mysql | 2024-08-23T10:19:11.172572Z 0 [Note] InnoDB: Highest supported file format is Barracuda. ragflow-mysql | 2024-08-23T10:19:11.192782Z 0 [Note] InnoDB: Creating shared tablespace for temporary tables ragflow-mysql | 2024-08-23T10:19:11.192852Z 0 [Note] InnoDB: Setting file './ibtmp1' size to 12 MB. Physically writing the file full; Please wait ... ragflow-mysql | 2024-08-23T10:19:11.210930Z 0 [Note] InnoDB: File './ibtmp1' size is now 12 MB. ragflow-mysql | 2024-08-23T10:19:11.211498Z 0 [Note] InnoDB: 96 redo rollback segment(s) found. 96 redo rollback segment(s) are active. ragflow-mysql | 2024-08-23T10:19:11.211511Z 0 [Note] InnoDB: 32 non-redo rollback segment(s) are active. ragflow-mysql | 2024-08-23T10:19:11.211797Z 0 [Note] InnoDB: Waiting for purge to start ragflow-mysql | 2024-08-23T10:19:11.262166Z 0 [Note] InnoDB: 5.7.18 started; log sequence number 246681350 ragflow-mysql | 2024-08-23T10:19:11.262482Z 0 [Note] InnoDB: Loading buffer pool(s) from /var/lib/mysql/ib_buffer_pool ragflow-mysql | 2024-08-23T10:19:11.262719Z 0 [Note] Plugin 'FEDERATED' is disabled. ragflow-mysql | 2024-08-23T10:19:11.268025Z 0 [Note] Found ca.pem, server-cert.pem and server-key.pem in data directory. Trying to enable SSL support using them. ragflow-mysql | 2024-08-23T10:19:11.268097Z 0 [Warning] Failed to set up SSL because of the following SSL library error: TLS version is invalid ragflow-mysql | 2024-08-23T10:19:11.268397Z 0 [Note] Server hostname (bind-address): '*'; port: 3306 ragflow-mysql | 2024-08-23T10:19:11.268464Z 0 [Note] IPv6 is available. ragflow-mysql | 2024-08-23T10:19:11.268469Z 0 [Note] - '::' resolves to '::'; ragflow-mysql | 2024-08-23T10:19:11.268484Z 0 [Note] Server socket created on IP: '::'. ragflow-mysql | 2024-08-23T10:19:11.270852Z 0 [Note] InnoDB: Buffer pool(s) load completed at 240823 18:19:11 ragflow-mysql | 2024-08-23T10:19:11.273835Z 0 [Warning] 'user' entry 'root@localhost' ignored in --skip-name-resolve mode. ragflow-mysql | 2024-08-23T10:19:11.273864Z 0 [Warning] 'user' entry 'mysql.sys@localhost' ignored in --skip-name-resolve mode. ragflow-mysql | 2024-08-23T10:19:11.273914Z 0 [Warning] 'db' entry 'sys mysql.sys@localhost' ignored in --skip-name-resolve mode. ragflow-mysql | 2024-08-23T10:19:11.273959Z 0 [Warning] 'proxies_priv' entry '@ root@localhost' ignored in --skip-name-resolve mode. ragflow-mysql | 2024-08-23T10:19:11.286518Z 0 [Warning] 'tables_priv' entry 'sys_config mysql.sys@localhost' ignored in --skip-name-resolve mode. ragflow-mysql | 2024-08-23T10:19:11.307744Z 0 [Note] Event Scheduler: Loaded 0 events ragflow-mysql | 2024-08-23T10:19:11.307955Z 0 [Note] Execution of init_file '/data/application/init.sql' started. ragflow-mysql | 2024-08-23T10:19:11.308796Z 0 [Note] Execution of init_file '/data/application/init.sql' ended. ragflow-mysql | 2024-08-23T10:19:11.308868Z 0 [Note] mysqld: ready for connections. ragflow-mysql | Version: '5.7.18' socket: '/var/run/mysqld/mysqld.sock' port: 3306 MySQL Community Server (GPL) ragflow-mysql | 2024-08-23T10:19:11.308877Z 0 [Note] Executing 'SELECT * FROM INFORMATION_SCHEMA.TABLES;' to get a list of tables using the deprecated partition engine. You may use the startup option '--disable-partition-engine-check' to skip this check. ragflow-mysql | 2024-08-23T10:19:11.308878Z 0 [Note] Beginning of list of non-natively partitioned tables ragflow-mysql | 2024-08-23T10:19:11.332534Z 0 [Note] End of list of non-natively partitioned tables ragflow-minio | ragflow-minio | You are running an older version of MinIO released 8 months before the latest release ragflow-minio | Update: Run mc admin update ragflow-minio | ragflow-minio | ragflow-es-01 | Created elasticsearch keystore in /usr/share/elasticsearch/config/elasticsearch.keystore ragflow-es-01 | Aug 23, 2024 6:19:15 PM sun.util.locale.provider.LocaleProviderAdapter ragflow-es-01 | WARNING: COMPAT locale provider will be removed in a future release ragflow-es-01 | {"@timestamp":"2024-08-23T10:19:15.824Z", "log.level": "INFO", "message":"Java vector incubator API enabled; uses preferredBitSize=256", "ecs.version": "1.2.0","service.name":"ES_ECS","event.dataset":"elasticsearch.server","process.thread.name":"main","log.logger":"org.apache.lucene.internal.vectorization.PanamaVectorizationProvider","elasticsearch.node.name":"es01","elasticsearch.cluster.name":"docker-cluster"} ragflow-es-01 | {"@timestamp":"2024-08-23T10:19:16.251Z", "log.level": "INFO", "message":"version[8.11.3], pid[175], build[docker/64cf052f3b56b1fd4449f5454cb88aca7e739d9a/2023-12-08T11:33:53.634979452Z], OS[Linux/6.10.0-linuxkit/amd64], JVM[Oracle Corporation/OpenJDK 64-Bit Server VM/21.0.1/21.0.1+12-29]", "ecs.version": "1.2.0","service.name":"ES_ECS","event.dataset":"elasticsearch.server","process.thread.name":"main","log.logger":"org.elasticsearch.node.Node","elasticsearch.node.name":"es01","elasticsearch.cluster.name":"docker-cluster"} ragflow-es-01 | {"@timestamp":"2024-08-23T10:19:16.252Z", "log.level": "INFO", "message":"JVM home [/usr/share/elasticsearch/jdk], using bundled JDK [true]", "ecs.version": "1.2.0","service.name":"ES_ECS","event.dataset":"elasticsearch.server","process.thread.name":"main","log.logger":"org.elasticsearch.node.Node","elasticsearch.node.name":"es01","elasticsearch.cluster.name":"docker-cluster"}

kkrusher avatar Aug 23 '24 10:08 kkrusher

0.14.0 improved system healthy monitoring. Please upgrade.

yuzhichang avatar Nov 28 '24 08:11 yuzhichang