image: repository: tccr.io/truecharts/docspell-server tag: v0.38.0@sha256:8f2fbd17bbbee0466d99ce4cb7bb0cf809cd01ab9e9fd67197a6dcbe03f92d35 pullPolicy: IfNotPresent joexImage: repository: tccr.io/truecharts/docspell-joex tag: v0.38.0@sha256:9f1774c462d64fc1d3dd8f8a3cae9d065b14202c1fffad0fbaf6d220877b7ffe pullPolicy: IfNotPresent dscImage: repository: tccr.io/truecharts/docspell-dsc tag: v0.9.0@sha256:829b2bc83fdfddc8127baef5b1149d96dcf0d5ca93f210fcf1344899c36b400e pullPolicy: IfNotPresent args: - /opt/server.conf podSecurityContext: runAsUser: 0 runAsGroup: 0 securityContext: runAsNonRoot: false readOnlyRootFilesystem: false dsc: # -- You need to enable integration endpoint with HTTP Header in rest server # -- If you enable allowed IPs you also need 127.0.0.1 as an entry there enabled: false # move | delete imported_action: move not_match_glob: "**/.*" match_glob: "" language: "" tag: "" rest_server: # -- App name, shows on the top right corner app_name: Docspell base_url: "" logging: # -- The format for the log messages. Can be one of: # -- Json | Logfmt | Fancy | Plain format: Fancy # -- The minimum level to log. From lowest to highest: # -- Trace | Debug | Info | Warn | Error minimum_level: Warn levels: # -- Override the log level of specific loggers docspell: Info flywaydb: Info binny: Info http4s: Info server_opts: # -- Enable HTTP2 enable_http2: false # -- Maximum allowed connections max_connections: 1024 # -- Timeout for waiting for the first output of the response response_timeout: 45s # -- This is a hard limit to restrict the size of a batch that is returned when searching for items. max_item_page_size: 200 # -- The number of characters to return for each item notes when searching. max_note_length: 180 # -- This defines whether the classification form in the collective settings is displayed or not. show_classification_settings: true auth: # -- How long a authentication token is valid session_valid: 5 minutes remember_me: enabled: true # -- How long the remember me cookie/token is valid. valid: 30 days download_all: # -- How many files to allow in a zip. max_files: 500 # -- The maximum (uncompressed) size of the zip file contents. max_size: 1400M openid: - enabled: false display: Keycloak provider: provider_id: keycloak client_id: docspell client_secret: example-secret-439e-bf06-911e4cdd56a6 scope: profile authorize_url: http://localhost:8080/auth/realms/home/protocol/openid-connect/auth token_url: http://localhost:8080/auth/realms/home/protocol/openid-connect/token user_url: "" logout_url: http://localhost:8080/auth/realms/home/protocol/openid-connect/logout sign_key: b64:anVzdC1hLXRlc3Q= sig_algo: RS512 collective_key: lookup:docspell_collective user_key: preferred_username - enabled: false display: Github provider: provider_id: github client_id: client_secret: scope: "" authorize_url: https://github.com/login/oauth/authorize token_url: https://github.com/login/oauth/access_token user_url: https://api.github.com/user logout_url: "" sign_key: "" sig_algo: RS256 collective_key: fixed:demo user_key: login oidc_auto_redirect: true integration_endpoint: enabled: false # -- The priority to use when submitting files through this endpoint. # low | high priority: low # -- The name used for the item "source" property when uploaded through this endpoint. source_name: integration allowed_ips: enabled: false ips: - "127.0.0.1" http_basic_auth: enabled: false realm: Docspell Integration user: docspell-int password: docspell-int http_header: enabled: false header_name: Docspell-Integration header_value: some-secret admin_endpoint: # -- Disables endpoint if empty secret: "" full_text_search: solr: # -- Used to tell solr when to commit the data commit_within: 1000 # -- If true, logs request and response bodies log_verbose: false def_type: lucene # -- The default combiner for tokens. One of AND | OR q_op: OR backend: # -- Enable or disable debugging for e-mail related functionality mail_debug: false database_schema: # -- Whether to run main database migrations. run_main_migrations: true # -- Whether to run the fixup migrations. run_fixup_migrations: true # -- Use with care. This repairs all migrations in the database by updating their checksums and removing failed migrations. repair_schema: false signup: # -- The mode defines if new users can signup or not. # open | invite | closed mode: open # -- This is the period an invitation token is considered valid. invite_time: 3 days files: # -- Defines the chunk size (in bytes) used to store the files. chunk_size: 524288 # -- The file content types that are considered valid. valid_mime_types: [] # database | minio | filesystem default_store: database stores: database: enabled: true minio: enabled: false endpoint: http://localhost:9000 access_key: access_key secret_key: secret_key bucket: docspell # -- Highly NOT recommended filesystem: enabled: false directory: /documents addons: # TODO: Check how exactly addons work. There are mentions of docker daemon enabled: false # -- Whether installing addons requiring network should be allowed or not. allow_impure: true # -- Define patterns of urls that are allowed to install addons from. allowed_urls: - "*" # -- Define patterns of urls that are denied to install addons from. denied_urls: [] joex: logging: # -- The format for the log messages. Can be one of: # -- Json | Logfmt | Fancy | Plain format: Fancy # -- The minimum level to log. From lowest to highest: # -- Trace | Debug | Info | Warn | Error minimum_level: Warn levels: # -- Override the log level of specific loggers docspell: Info flywaydb: Info binny: Info http4s: Info database_schema: # -- Whether to run main database migrations. run_main_migrations: false # -- Whether to run the fixup migrations. run_fixup_migrations: true # -- Use with care. This repairs all migrations in the database by updating their checksums and removing failed migrations. repair_schema: false # -- Enable or disable debugging for e-mail related functionality. This applies to both sending and receiving mails. mail_debug: false send_mail: # -- This is used as the List-Id e-mail header when mails are sent from docspell to its users list_id: "" scheduler: # -- Number of processing allowed in parallel. pool_size: 1 # -- A counting scheme determines the ratio of how high and low priority jobs are run. counting_scheme: 4,1 # -- How many times a failed job should be retried until it enters failed state. retries: 2 # -- The delay until the next try is performed for a failed job. retry_delay: 1 minute # -- The queue size of log statements from a job. log_buffer_size: 500 # -- If no job is left in the queue, the scheduler will wait until a notify is requested. wakeup_period: 30 minutes periodic_scheduler: # -- A fallback to start looking for due periodic tasks regularly. wakeup_period: 10 minutes user_tasks: scan_mailbox: # -- A limit of how many folders to scan through. max_folders: 50 # -- How many mails (headers only) to retrieve in one chunk. mail_chunk_size: 50 # -- A limit on how many mails to process in one job run. max_mails: 500 house_keeping: # -- When the house keeping tasks execute. schedule: Sun *-*-* 00:00:00 UTC # -- This task removes invitation keys that have been created but not used. cleanup_invites: # -- Whether this task is enabled. enabled: true # -- The minimum age of invites to be deleted. older_than: 30 days # -- This task removes expired remember-me tokens. cleanup_remember_me: # -- Whether this task is enabled. enabled: true # -- The minimum age of tokens to be deleted. older_than: 30 days # -- Jobs store their log output in the database. cleanup_jobs: # -- Whether this task is enabled. enabled: true # -- The minimum age of jobs to delete. older_than: 30 days # -- This defines how many jobs are deleted in one transaction. delete_batch: 100 # -- Zip files created for downloading multiple files are cached and can be cleared periodically. cleanup_downloads: # -- Whether this task is enabled. enabled: true # -- The minimum age of a download file to be deleted. older_than: 14 days # -- Removes node entries that are not reachable anymore. check_nodes: # -- Whether this task is enabled. enabled: true # -- How often the node must be unreachable, before it is removed. min_not_found: 2 # -- Checks all files against their checksum integrity_check: enabled: true # -- A periodic task to check for new releases of docspell. update_check: # -- Whether to enable this task enabled: false # -- Sends the mail without checking the latest release. test_run: false # -- When the update check should execute. schedule: "Sun *-*-* 00:00:00 UTC" # -- An account id in form of `collective/user` sender_account: "" # -- The SMTP connection id that should be used for sending the mail. smtp_id: "" # -- A list of recipient e-mail addresses. recipients: [] # -- The subject of the mail. subject: Docspell {{ latestVersion }} is available # -- The body of the mail. body: | Hello, You are currently running Docspell {{ currentVersion }}. Version *{{ latestVersion }}* is now available, which was released on {{ releasedAt }}. Check the release page at Have a nice day! Docspell Update Check # -- Configuration of text extraction extraction: pdf: min_text_length: 500 preview: # -- When rendering a pdf page, use this dpi. dpi: 32 ocr: # -- Images greater than this size are skipped. max_image_size: 14000000 page_range: # -- Defines what pages to process. begin: 10 # -- The ghostscript command. ghostscript: command: program: gs args: - -dNOPAUSE - -dBATCH - -dSAFER - -sDEVICE=tiffscaled8 - "-sOutputFile={{outfile}}" - "{{infile}}" timeout: 5 minutes working_dir: /tmp/docspell-extraction # -- The unpaper command. unpaper: command: program: unpaper args: - "{{infile}}" - "{{outfile}}" timeout: 5 minutes # -- The tesseract command. tesseract: command: program: tesseract args: - "{{file}}" - stdout - -l - "{{lang}}" timeout: 5 minutes text_analysis: # -- Maximum length of text to be analyzed. max_length: 0 working_dir: /tmp/docspell-analysis nlp: # -- The mode for configuring NLP models # -- full | basic | regexonly | disabled mode: full clear_interval: 15 minutes # -- Restricts proposals for due dates. max_due_date_years: 10 regex_ner: # -- Whether to enable custom NER annotation. max_entries: 1000 file_cache_time: 1 minute classification: # -- Whether to enable classification globally. enabled: true # -- This limit and `text-analysis.max-length` define how much memory is required. item_count: 600 # -- Enclose regexps in triple quotes. classifiers: useSplitWords: true splitWordsTokenizerRegexp: '"""[\p{L}][\p{L}0-9]*|(?:\$ ?)?[0-9]+(?:\.[0-9]{2})?%?|\s+|."""' splitWordsIgnoreRegexp: '"""\s+"""' useSplitPrefixSuffixNGrams: true maxNGramLeng: 4 minNGramLeng: 1 splitWordShape: chris4 intern: true # -- Configuration for converting files into PDFs. convert: # -- The chunk size used when storing files. chunk_size: 524288 # -- A string used to change the filename of the converted pdf file. converted_filename_part: converted # -- When reading images, this is the maximum size. max_image_size: 14000000 markdown: # -- The CSS that is used to style the resulting HTML. internal_css: "body { padding: 2em 5em; }" wkhtmlpdf: command: program: wkhtmltopdf args: - -s - A4 - --encoding - "{{enconding}}" - --load-error-handling - ignore - --load-media-error-handling - ignore - "-" - "{{outfile}}" timeout: 2 minutes working_dir: /tmp/docspell-convert tesseract: command: program: tesseract args: - "{{infile}}" - out - -l - "{{lang}}" - pdf - txt timeout: 5 minutes working_dir: /tmp/docspell-convert unoconv: command: program: unoconv args: - -f - pdf - -o - "{{outfile}}" - "{{infile}}" timeout: 5 minutes working_dir: /tmp/docspell-convert ocrmypdf: enabled: true command: program: ocrmypdf args: - -l - "{{lang}}" - --skip-text - --deskew - -j - "1" - "{{infile}}" - "{{outfile}}" timeout: 5 minutes working_dir: /tmp/docspell-convert decrypt_pdf: enabled: true passwords: [] files: # -- Defines the chunk size (in bytes) used to store the files. chunk_size: 524288 # -- The file content types that are considered valid. valid_mime_types: [] # database | minio | filesystem default_store: database stores: database: enabled: true minio: enabled: false endpoint: http://localhost:9000 access_key: access_key secret_key: secret_key bucket: docspell # -- Highly NOT recommended filesystem: enabled: false directory: /documents full_text_search: solr: # -- Used to tell solr when to commit the data commit_within: 1000 # -- If true, logs request and response bodies log_verbose: false def_type: lucene # -- The default combiner for tokens. One of AND | OR q_op: OR migration: index_all_chunk: 10 addons: # TODO: Check TODO above for addons working_dir: /tmp/docspell-addons cache_dir: /tmp/docspell-addons-cache executor_config: runner: trivial fail_fast: true run_timeout: 15 minutes probes: liveness: type: HTTP path: /api/info/version readiness: type: HTTP path: /api/info/version startup: type: HTTP path: /api/info/version service: main: ports: main: port: 10320 protocol: HTTP joex: enabled: true type: ClusterIP ports: joex: enabled: true port: 10321 protocol: HTTP persistence: server: enabled: true type: secret readOnly: true defaultMode: "0600" objectName: '{{ include "tc.common.names.fullname" . }}-server-secret' mountPath: /opt/server.conf subPath: server.conf joex: enabled: true type: secret noMount: true readOnly: true defaultMode: "0600" objectName: '{{ include "tc.common.names.fullname" . }}-joex-secret' mountPath: /opt/joex.conf subPath: joex.conf import: enabled: true noMount: true mountPath: /import postgresql: enabled: true existingSecret: dbcreds postgresqlUsername: docspell postgresqlDatabase: docspell solr: enabled: true existingSecret: solrcreds solrCores: docspell solrUsername: docspell solrEnableAuthentication: "no" portal: enabled: true