Page Comparison

## Replica set configuration (non-EC2/AWS installations only): comma-separated list of either all IPs or all hostnames within a replica set, semi-colon-separated for multiple replica sets
# (eg "A,B;C,D" where A-D are IP addresses or hostnames would create 2 shards with 2 hosts each "A,B;A,B" would create 2 shards both on the same replica set, etc)
db.replica.sets=
#----------------------------------------------
# db.cluster.subnet -----------------------------------
# 1.9] UI settings
#-------------------------------------------------------------------------------
# The passphrase for the SSL keystore (not needed unless HTTPS is being used)
ssl.passphrase=
# This is a regex that, if specified, will allow only access to REST commands matching
# the pattern - only applied to remote clients. Connections from localhost always have access 
# to everything
# Eg the commented out example will allow only login/keepalive and querying.
#remote.access.allow=^/api/(knowledge/document/query|auth/login|auth/keepalive)
remote.access.allow=
# This parameter does the opposite, allows everything except specified commands
remote.access.deny=

#-- used for non-EC2/AWS only installations to help mongodb configurations
# identify proper host ip addresses, e.g. 127.0.0. - these are compared against the IPs in db.replica.sets
# Can also be one of the following: if blank then assumes that the db.replica.sets will be a list of short hostnames - if "FQDN" then assumes that the db.replica.sets will be a list of fully qualified hostnames
db.cluster.subnet=

#-------------------------------------------------------------------------------
# 1.13] Entity Extractor Properties
#-------------------------------------------------------------------------------
# Alchemy and Open Calais Keys:
# (Obtain from alchemyapi.com or opencalais.com)
extractor.key.alchemyapi=
extractor.key.opencalais=
#----------------------------------------------
# Entity extraction type selection: opencalais or alchemyapi or none
# ("opencalais" has a much higher limit than "alchemyapi" (1000/day) so is recommended for free use
#  "alchemyapi" extracts sentiment, "opencalais" extracts entity associations Note this can be overridden per source)
extractor.entity.default=
# Text extraction type selection: boilerpipe or alchemyapi or none
# ("alchemyapi" is much better, but has the limit discussed above. Note this can be overridden per source)
extractor.text.default=

# If this is set to true then custom (Hadoop) plugins will run locally on this node, without 
# a Hadoop cluster needing to be set up (which is complicated to do) - the downside of course is that
# jobs will not scale across many nodes. Set this to true for single-node clusters and before Hadoop
# has been installed.
hadoop.local_mode=false

#-----for details: 
s3.gpg.passphrase=

#--------------------------------(server/port should normally point to localhost:27017), where API nodes have a mongos
db.server=localhost
db.port= 27017
# db.sharded - 0 = false and 1 = true
db.sharded=1
# The max number of documents to store (eg 10M). Docs will be dropped in order of age.
# (Not currently supported):
db.capacity=10000000
# MongoDB config server or servers (must be 1 or 3 comma separated IPs), non-EC2/AWS installations only
db.config.servers=
db.replica.sets=
#-----------------------------------------------
# 2.10] Elasticsearch Propertiesdb.cluster.subnet - used for non-EC2/AWS only installations to help mongodb configurations
# identify proper host ip addresses, e.g. 127.0.0.
db.cluster.subnet=
#----------------------------------------------
# DiscoveryThe modelocation =from ec2which (ifto runningfetch on AWS) or zen (specify a list of IPs below):
elastic.node.discovery=ec2
#----------------------------------------------
# ES nodes, e.g.: elastic.search.nodes='NODE1:9300','NODE2:9300','NODE3:9300':
# Needed if discovery.mode=zen (not EC2/AWS), a set of IPs to try (>= 1 must be running elasticsearch)
elastic.search.nodes=
#---the geo.bson dump used for feature.geo
# can start s3://, http:// or https://, else is assumed to be a file, eg
#db.geo_archive=s3://config.saas.infinite.ikanow.com/geo.bson.tar.gz
# Can always be retrieved here
db.geo_archive=http://yum.ikanow.com/infinit.e-preinstall/artifacts/geo.bson.tar.gz

#------------2.9] UI inactivity timeout (in seconds)
#-------------------------------------------------------------------------------
# 2.11] Harvester Properties
#-------------------------------------------------------------------------------
# Comma-separated-list from File,Database,Feed (note Database and Feed need jars not bundled with the RPM)
harvester.types=File,Database,Feed
# Web crawling etiquette: the time to way between consecutive accesses to the same time (10s is standard)
harvest.feed.wait=10000
# The minimum time between consecutive harvests (avoids thrashing FS/DB/RSS when there's nothing to get)
harvest.mintime.ms=300000
# The minimum time between consecutive source harvests (set if needs to be longer than harvest.mintime.ms,
# eg if you want to pick up a source quickly the first time but then not update so frequently)
harvest.source.mintime.ms=
# Restricts the number of docs that can be harvested per cycle for memory reasons:
harvest.maxdocs_persource=5000
# Threading configuration type:num_threads (type from above):
# (eg for RSS heavy increase the "feed", for DB heavy increase the "file" etc. Beyond 20 there is limited benefit). 
harvest.threads=file:5,database:5,feed:20
# This controls the batch size of sources picked up by a thread, this does not normally need to be changed (its default is shown)
# (It can be reduced in cases where a small number of very long-running sources need to be harvested).
#harvest.distribution.batch.harvest=20
# This disables entity and association aggregation. For almost all applications you will not want to set this.
#harvest.disable_aggregation=false

 #
# Discovery mode = ec2 (if running on AWS) or zen (specify a list of IPs below):
elastic.node.discovery=ec2
#--------------------------------------------------------
# ES nodes, e.g.: elastic.search.nodes='NODE1:9300','NODE2:9300','NODE3:9300':
# Needed if discovery.mode=zen (not EC2/AWS), a set of IPs to try (>= 1 must be running elasticsearch)
elastic.search.nodes=
#------------------------------
# 2.13] Entity Extractor Properties
#--------------------------------------------------------------------------------
# Alchemymlockall extraction= levelshould # 1==people postproc, 2==geo postproc, 3==both
# (This uses some hard-coded heuristics to work around known AlchemyAPI errors)
app.alchemy.postproc=3

#-------------------------------------------------------------------------------
# 2.15] Maps API key:Comma-separated-list from File,Database,Feed (note Database and Feed need jars not bundled with the RPM)
harvester.types=File,Database,Feed
# Web crawling etiquette: the time to way between consecutive accesses to the same time (10s is standard)
harvest.feed.wait=10000
# The minimum time between consecutive harvests (avoids thrashing FS/DB/RSS when there's nothing to get)
harvest.mintime.ms=300000
# The minimum time between consecutive source harvests (set if needs to be longer than harvest.mintime.ms,
# eg if you want to pick up a source quickly the first time but then not update so frequently)
harvest.source.mintime.ms=
# Restricts the number of docs that can be harvested per cycle for memory reasons:
harvest.maxdocs_persource=5000
# Threading configuration type:num_threads (type from above):
# (eg for RSS heavy increase the "feed", for DB heavy increase the "file" etc. Beyond 20 there is limited benefit). 
harvest.threads=file:5,database:5,feed:20
# This controls the batch size of sources picked up by a thread, this does not normally need to be changed (its default is shown)
# (It can be reduced in cases where a small number of very long-running sources need to be harvested).
#harvest.distribution.batch.harvest=20
# This disables entity and association aggregation. For almost all applications you will not want to set this.
#harvest.disable_aggregation=false
# This controls what % of 1 CPU is used to update entity and association counts and synchronization, shouldn't need to change it
# (Reducing it will speed up raw harvest speeds, Increasing it will keep entity etc freqs more up-to-date)
#harvest.aggregation.duty_cycle=0.5
# This parameter uses the Java Security Manager to prevent scripts accessing local network services (at the expense of some performance)
# It can be turned off for uses of the platform where sources must be approved before being added (etc)
harvest.security=false
# This is a comma-separated list of hosts in the following format "http://<HOST>[:<PORT>]" or "socks://<HOST>:<PORT>"
# When specified, all requests for external content from the harvester are proxied (round-robin) through the specified hosts
harvest.proxy=
# Content controls:
#This is the maximum size of content (before gzip) that will be stored (truncated above this)
#store.maxcontent=16000000
#If true (default false), stores the raw content of a document (as well as the post-processed text)
#store.rawcontent=false
#If true (default false), then the doc_content.gzip_content also contains the JSON metadata, stored as a string 
#store.metadata_as_content=false