ycb 2.0.0__tar.gz

ycb-2.0.0/.env.example

@@ -0,0 +1,259 @@
+# Enabled Connectors (comma-separated list, leave empty to enable all configured connectors)
+# Available: slack, google_docs, github, notion, discord, google_sheets, linear, outlook, teams, gitlab, dropbox, mixpanel, amplitude, algolia, exa, perplexity, facebook
+CONNECTORS_ENABLED=slack,google_docs,github,notion,discord,google_sheets,linear,outlook,teams,gitlab,dropbox,mixpanel,amplitude,algolia,exa,perplexity,facebook
+
+# === Performance & Concurrency Configuration ===
+# Hardware Guidance: Low-VRAM/consumer GPUs (e.g. 4GB-8GB VRAM) should keep these low (1-2)
+# to avoid GPU memory exhaustion. High-end or server-grade hardware can increase them for higher throughput.
+LLM_CONCURRENCY=1   # Number of concurrent chunk inference requests sent to Ollama (default: 1)
+BATCH_SIZE=2        # Number of documents processed per interactive sync batch pause (default: 2)
+
+# === Tier 1 Connectors ===
+
+# 1. Slack Configuration
+SLACK_BOT_TOKEN=xoxb-your-token
+SLACK_APP_TOKEN=xapp-your-token
+
+# 2. Google Docs & Sheets Configuration
+GOOGLE_CREDENTIALS_PATH=credentials.json
+
+# 3. GitHub Configuration
+GITHUB_TOKEN=ghp_your_personal_access_token
+GITHUB_REPOS=owner/repo1,owner/repo2
+
+# 4. Notion Configuration
+NOTION_TOKEN=secret_your_notion_integration_token
+
+# 5. Discord Configuration
+DISCORD_BOT_TOKEN=your_discord_bot_token
+DISCORD_GUILD_IDS=123456789012345678
+
+# 6. Linear Configuration
+LINEAR_API_KEY=lin_api_your_linear_key
+
+# 7. Microsoft Outlook & Teams Configuration
+MS_CLIENT_ID=your_azure_client_id
+MS_CLIENT_SECRET=your_azure_client_secret
+MS_TENANT_ID=your_azure_tenant_id
+
+# === Tier 2 Connectors ===
+
+# 8. GitLab Configuration
+GITLAB_TOKEN=glpat-your_personal_access_token
+GITLAB_URL=https://gitlab.com
+GITLAB_PROJECTS=group/project1,group/project2
+
+# 9. Dropbox Configuration
+DROPBOX_TOKEN=sl.your_dropbox_access_token
+
+# 10. Mixpanel Configuration
+MIXPANEL_API_SECRET=your_mixpanel_api_secret
+MIXPANEL_PROJECT_ID=your_project_id
+
+# 11. Amplitude Configuration
+AMPLITUDE_API_KEY=your_amplitude_api_key
+AMPLITUDE_SECRET_KEY=your_amplitude_secret_key
+
+# 12. Algolia Configuration
+ALGOLIA_APP_ID=your_algolia_app_id
+ALGOLIA_API_KEY=your_algolia_api_key
+ALGOLIA_INDEX_NAME=your_index_name
+
+# 13. Exa Search Configuration
+EXA_API_KEY=your_exa_api_key
+EXA_SEARCH_QUERIES=company refund policy,server incident response
+
+# 14. Perplexity AI Configuration
+PERPLEXITY_API_KEY=pplx-your_perplexity_api_key
+PERPLEXITY_PROMPTS=What is our standard customer refund procedure?
+
+# 15. Facebook Configuration
+FACEBOOK_PAGE_TOKEN=EAAG...your_page_access_token
+FACEBOOK_PAGE_ID=me
+
+# === Batch 1 Connectors ===
+
+# 16. Gmail Configuration (Uses shared GOOGLE_CREDENTIALS_PATH)
+# Requires 'https://www.googleapis.com/auth/gmail.readonly' scope in Google Cloud Console
+
+# 17. Google Drive Configuration (Uses shared GOOGLE_CREDENTIALS_PATH)
+# Requires 'https://www.googleapis.com/auth/drive.readonly' scope in Google Cloud Console
+
+# 18. Todoist Configuration
+# Get from Todoist -> Settings -> Integrations -> Developer -> API token
+TODOIST_API_TOKEN=your_todoist_api_token
+
+# 19. Web Crawler Configuration
+# Comma-separated list of starting URLs to crawl
+CRAWLER_START_URLS=https://example.com/docs,https://example.com/help
+CRAWLER_MAX_PAGES=50
+CRAWLER_MAX_DEPTH=2
+CRAWLER_ALLOWED_DOMAINS=example.com
+CRAWLER_DELAY_SECONDS=2
+CRAWLER_REQUEST_TIMEOUT_SECONDS=10
+CRAWLER_MAX_RUNTIME_SECONDS=300
+
+# === Batch 2 Connectors ===
+
+# 20. Jira Configuration
+# Get API token from https://id.atlassian.com/manage-profile/security/api-tokens
+JIRA_DOMAIN=your-company.atlassian.net
+JIRA_EMAIL=your_email@company.com
+JIRA_API_TOKEN=your_jira_api_token
+
+# 21. Asana Configuration
+# Get token from Asana -> My Settings -> Developer -> Personal Access Tokens
+ASANA_TOKEN=1/your_asana_personal_access_token
+ASANA_WORKSPACE_GID=your_workspace_gid
+
+# 22. Calendly Configuration
+# Get token from Calendly -> Account Settings -> Integrations -> API & Webhooks
+CALENDLY_TOKEN=your_calendly_personal_access_token
+# WARNING: Setting CALENDLY_INGEST_INVITEE_DETAILS=true will ingest external meeting invitees'
+# personally identifiable information (PII) including full names, email addresses, and booking intake
+# Q&A responses into local processing and exported skills files. Keep set to false (default) unless opt-in is required.
+CALENDLY_INGEST_INVITEE_DETAILS=false
+
+# 23. ClickUp Configuration
+# Get token from ClickUp -> Settings -> Apps -> API Token
+CLICKUP_API_TOKEN=pk_your_clickup_api_token
+CLICKUP_TEAM_ID=your_team_id
+
+# === Batch 3a Connectors ===
+
+# 24. Airtable Configuration
+# Create a Personal Access Token at https://airtable.com/create/tokens
+# Required scopes: data.records:read, schema.bases:read
+AIRTABLE_TOKEN=your_airtable_personal_access_token
+# Optional: comma-separated base IDs to limit ingestion (leave empty to discover all accessible bases)
+AIRTABLE_BASE_IDS=appXXXXXXXXXXXXXX,appYYYYYYYYYYYYYY
+
+# 25. Datadog Configuration
+# API Key: https://app.datadoghq.com/organization-settings/api-keys
+# Application Key: https://app.datadoghq.com/organization-settings/application-keys
+DATADOG_API_KEY=your_datadog_api_key
+DATADOG_APP_KEY=your_datadog_application_key
+# Optional: change if using a non-US Datadog site (e.g. datadoghq.eu, us3.datadoghq.com)
+DATADOG_SITE=datadoghq.com
+
+# 26. Segment Configuration
+# Create a Personal Access Token at https://app.segment.com/workspaces/YOUR_WORKSPACE/settings/access-management
+# Required scope: Workspace Member (read access to sources, destinations, tracking plans)
+SEGMENT_ACCESS_TOKEN=your_segment_personal_access_token
+
+# 27. Front Configuration
+# Generate an API token from Front Settings > Developers > API tokens (requires admin privileges)
+# A free developer account is available at https://dev.frontapp.com/
+FRONT_API_TOKEN=your_front_api_token
+
+# 28. Zoom Configuration
+# Create a Server-to-Server OAuth app in the Zoom App Marketplace:
+# https://marketplace.zoom.us/develop/create — choose "Server-to-Server OAuth"
+# Required scopes: meeting:read:meeting:admin, recording:read:recording:admin, user:read:user:admin
+ZOOM_ACCOUNT_ID=your_zoom_account_id
+ZOOM_CLIENT_ID=your_zoom_client_id
+ZOOM_CLIENT_SECRET=your_zoom_client_secret
+
+# 29. X / Twitter Configuration
+# Create a developer app at https://developer.twitter.com/en/portal/dashboard
+# NOTE: As of 2025, free-tier X developer accounts have very limited read access.
+# A Basic plan ($100/month) or higher is required for meaningful tweet search and timeline access.
+# This connector handles 401/403 responses gracefully — it logs a clear message and returns no data
+# rather than crashing. Set the vars below if you have an eligible plan.
+TWITTER_BEARER_TOKEN=your_x_twitter_bearer_token
+# Comma-separated search queries (e.g. your company name, product, brand)
+TWITTER_SEARCH_QUERIES=your_company_name,your_product_name
+# Optional: comma-separated numeric user IDs whose timelines to fetch
+TWITTER_USER_IDS=
+
+# === Batch 3b Connectors ===
+
+# 30. HubSpot Configuration
+# Create a Private App in HubSpot Settings > Integrations > Private Apps.
+# Required scopes: crm.objects.contacts.read, crm.objects.companies.read,
+#                  crm.objects.deals.read, crm.objects.notes.read
+HUBSPOT_ACCESS_TOKEN=your_hubspot_private_app_access_token
+
+# 31. Salesforce Configuration
+# Setup steps (Client Credentials Flow — server-to-server, no browser login required):
+#   1. In Salesforce Setup > App Manager, create a new Connected App with OAuth enabled.
+#   2. Under OAuth settings, enable "Enable Client Credentials Flow".
+#   3. Under the app's Manage > Edit Policies, set "Client Credentials Flow" Run As to a
+#      dedicated integration user (NOT yourself — this user's profile/permissions determine
+#      what data the connector can access).
+#   4. CRITICAL — permission set on the Run As user: the Client Credentials flow authenticates
+#      as the app itself, not as a named user. If the Run As user's profile or permission set
+#      does not include read access to Opportunity, Account, Case, and Note objects, the SOQL
+#      queries will return empty results with no error — the API call succeeds but returns 0
+#      records. Assign the Run As user a permission set that explicitly grants read access to
+#      all object types you want to ingest before running the connector.
+#   5. Retrieve the Consumer Key (client_id) and Consumer Secret (client_secret) from the app.
+# (Username-password OAuth is deprecated/blocked in orgs created after Summer '23.)
+SALESFORCE_CLIENT_ID=your_salesforce_connected_app_consumer_key
+SALESFORCE_CLIENT_SECRET=your_salesforce_connected_app_consumer_secret
+# Optional: use 'test' for sandbox orgs; defaults to 'login' (production)
+SALESFORCE_DOMAIN=login
+
+# 32. Monday.com Configuration
+# Get your API token from monday.com: avatar menu (top-right) > Developers > My Access Tokens
+MONDAY_API_TOKEN=your_monday_api_token
+
+# 33. Basecamp Configuration
+# Requires OAuth 2.0. Register an integration at https://launchpad.37signals.com/integrations
+# to get client_id/client_secret, complete the browser OAuth flow once to obtain an
+# access_token, then provide it here along with your numeric Basecamp account ID
+# (found in your Basecamp URL: https://3.basecamp.com/<ACCOUNT_ID>/).
+BASECAMP_ACCESS_TOKEN=your_basecamp_oauth_access_token
+BASECAMP_ACCOUNT_ID=your_basecamp_account_id
+# Required by Basecamp API policy — include your app name and contact email
+BASECAMP_USER_AGENT=CompanyBrain/1.0 (yourname@yourcompany.com)
+
+# === Batch 3c Connectors ===
+
+# 34. Ashby ATS Configuration
+# Ashby API keys are generated inside your Ashby account — no separate sign-up.
+# Navigate to: Ashby > Settings > Admin > Integrations > API Keys > + New Key
+# REQUIREMENT: You must be an existing Ashby customer with admin-level access.
+# There is no free tier or public sandbox — credentials require an active subscription.
+# Required scopes on the key: Jobs (read), Candidates (read), Organization (read)
+ASHBY_API_KEY=your_ashby_api_key
+
+# 35. BambooHR Configuration
+# API key path (for ingesting your own organisation's data — no OAuth required).
+# Generate: Log in to BambooHR > profile icon (lower-left) > API Keys > Add New Key
+# Your company subdomain is the part before .bamboohr.com in your URL.
+# Example: if you log in at https://acme.bamboohr.com, your subdomain is 'acme'.
+# NOTE: BambooHR API keys are strictly for your own organisation's internal use
+# per BambooHR's Terms of Service. This matches Company Brain's use case.
+BAMBOOHR_API_KEY=your_bamboohr_api_key
+BAMBOOHR_SUBDOMAIN=your_company_subdomain
+
+# 36. Deel Configuration
+# Generate an Organisation Token (not Personal) for server-to-server ingestion:
+# Deel Dashboard > More > Developer > Access Tokens > Generate new token
+# Choose "Organisation Token" — it doesn't expire when a user leaves the company.
+# A sandbox environment is available at api-sandbox.demo.deel.com for testing.
+DEEL_API_TOKEN=your_deel_organisation_token
+
+# 37. Rippling Configuration
+# Generate an API token: Rippling admin account > Tools > Developer > API Tokens
+# Requires admin-level access to the Rippling account.
+# IMPORTANT — Terms of Service constraint: This token is for your own organisation's
+# internal use only. It must NOT be used to access another company's Rippling data.
+# Company Brain's use case (each customer ingests their own data) is the permitted use.
+# For multi-tenant integrations, Rippling requires the Technology Partner Program + OAuth.
+# Rate limit: 300 requests per 10-second burst window per IP address.
+RIPPLING_API_TOKEN=your_rippling_api_token
+
+# === Core System Configuration ===
+
+# Ollama Configuration
+OLLAMA_MODEL=gemma4:e4b
+OLLAMA_HOST=http://localhost:11434
+
+# Storage Configuration
+DATABASE_URL=sqlite:///./data/company_brain.db
+
+# Application Configuration
+SYNC_INTERVAL_MINUTES=30
+KNOWLEDGE_EXTRACTION_BATCH_SIZE=5

ycb-2.0.0/.gitignore

@@ -0,0 +1,18 @@
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+.env
+venv/
+data/
+output/
+credentials.json
+token.pickle
+company_brain.log
+*.log
+*.db
+*.sqlite
+.DS_Store
+build/
+dist/
+*.egg-info/