go/pkg/rag/qdrant.go

226 lines
5.6 KiB
Go
Raw Normal View History

feat: wire release command, add tar.xz support, unified installers (#277) * feat(cli): wire release command and add installer scripts - Wire up `core build release` subcommand (was orphaned) - Wire up `core monitor` command (missing import in full variant) - Add installer scripts for Unix (.sh) and Windows (.bat) - setup: Interactive with variant selection - ci: Minimal for CI/CD environments - dev: Full development variant - go/php/agent: Targeted development variants - All scripts include security hardening: - Secure temp directories (mktemp -d) - Architecture validation - Version validation after GitHub API call - Proper cleanup on exit - PowerShell PATH updates on Windows (avoids setx truncation) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * feat(build): add tar.xz support and unified installer scripts - Add tar.xz archive support using Borg's compress package - ArchiveXZ() and ArchiveWithFormat() for configurable compression - Better compression ratio than gzip for release artifacts - Consolidate 12 installer scripts into 2 unified scripts - install.sh and install.bat with BunnyCDN edge variable support - Subdomains: setup.core.help, ci.core.help, dev.core.help, etc. - MODE and VARIANT transformed at edge based on subdomain - Installers prefer tar.xz with automatic fallback to tar.gz - Fixed CodeRabbit issues: HTTP status patterns, tar error handling, verify_install params, VARIANT validation, CI PATH persistence Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * chore: add build and release config files - .core/build.yaml - cross-platform build configuration - .core/release.yaml - release workflow configuration Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * chore: move plans from docs/ to tasks/ Consolidate planning documents in tasks/plans/ directory. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(install): address CodeRabbit review feedback - Add curl timeout (--max-time) to prevent hanging on slow networks - Rename TMPDIR to WORK_DIR to avoid clobbering system env var - Add chmod +x to ensure binary has execute permissions - Add error propagation after subroutine calls in batch file - Remove System32 install attempt in CI mode (use consistent INSTALL_DIR) - Fix HTTP status regex for HTTP/2 compatibility Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * feat(rag): add Go RAG implementation with Qdrant + Ollama Add RAG (Retrieval Augmented Generation) tools for storing documentation in Qdrant vector database and querying with semantic search. This replaces the Python tools/rag implementation with a native Go solution. New commands: - core rag ingest [directory] - Ingest markdown files into Qdrant - core rag query [question] - Query vector database with semantic search - core rag collections - List and manage Qdrant collections Features: - Markdown chunking by sections and paragraphs with overlap - UTF-8 safe text handling for international content - Automatic category detection from file paths - Multiple output formats: text, JSON, LLM context injection - Environment variable support for host configuration Dependencies: - github.com/qdrant/go-client (gRPC client) - github.com/ollama/ollama/api (embeddings API) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * feat(deploy): add pure-Go Ansible executor and Coolify API integration Implement infrastructure deployment system with: - pkg/ansible: Pure Go Ansible executor - Playbook/inventory parsing (types.go, parser.go) - Full execution engine with variable templating, loops, blocks, conditionals, handlers, and fact gathering (executor.go) - SSH client with key/password auth and privilege escalation (ssh.go) - 35+ module implementations: shell, command, copy, template, file, apt, service, systemd, user, group, git, docker_compose, etc. (modules.go) - pkg/deploy/coolify: Coolify API client wrapping Python swagger client - List/get servers, projects, applications, databases, services - Generic Call() for any OpenAPI operation - pkg/deploy/python: Embedded Python runtime for swagger client integration - internal/cmd/deploy: CLI commands - core deploy servers/projects/apps/databases/services/team - core deploy call <operation> [params-json] This enables Docker-free infrastructure deployment with Ansible-compatible playbooks executed natively in Go. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(deploy): address linter warnings and build errors - Fix fmt.Sprintf format verb error in ssh.go (remove unused stat command) - Fix errcheck warnings by explicitly ignoring best-effort operations - Fix ineffassign warning in cmd_ansible.go All golangci-lint checks now pass for deploy packages. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * style(deploy): fix gofmt formatting Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(deploy): use known_hosts for SSH host key verification Address CodeQL security alert by using the user's known_hosts file for SSH host key verification when available. Falls back to accepting any key only when known_hosts doesn't exist (common in containerized or ephemeral environments). Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * feat(ai,security,ide): add agentic MVP, security jobs, and Core IDE desktop app Wire up AI infrastructure with unified pkg/ai package (metrics JSONL, RAG integration), move RAG under `core ai rag`, add `core ai metrics` command, and enrich task context with Qdrant documentation. Add `--target` flag to all security commands for external repo scanning, `core security jobs` for distributing findings as GitHub Issues, and consistent error logging across scan/deps/alerts/secrets commands. Add Core IDE Wails v3 desktop app with Angular 20 frontend, MCP bridge (loopback-only HTTP server), WebSocket hub, and Claude Code bridge. Production-ready with Lethean CIC branding, macOS code signing support, and security hardening (origin validation, body size limits, URL scheme checks, memory leak prevention, XSS mitigation). Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix: address PR review comments from CodeRabbit, Copilot, and Gemini Fixes across 25 files addressing 46+ review comments: - pkg/ai/metrics.go: handle error from Close() on writable file handle - pkg/ansible: restore loop vars after loop, restore become settings, fix Upload with become=true and no password (use sudo -n), honour SSH timeout config, use E() helper for contextual errors, quote git refs in checkout commands - pkg/rag: validate chunk config, guard negative-to-uint64 conversion, use E() helper for errors, add context timeout to Ollama HTTP calls - pkg/deploy/python: fix exec.ExitError type assertion (was os.PathError), handle os.UserHomeDir() error - pkg/build/buildcmd: use cmd.Context() instead of context.Background() for proper Ctrl+C cancellation - install.bat: add curl timeouts, CRLF line endings, use --connect-timeout for archive downloads - install.sh: use absolute path for version check in CI mode - tools/rag: fix broken ingest.py function def, escape HTML in query.py, pin qdrant-client version, add markdown code block languages - internal/cmd/rag: add chunk size validation, env override handling Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(build): make release dry-run by default and remove darwin/amd64 target Replace --dry-run (default false) with --we-are-go-for-launch (default false) so `core build release` is safe by default. Remove darwin/amd64 from default build targets (arm64 only for macOS). Fix cmd_project.go to use command context instead of context.Background(). Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-04 00:49:57 +00:00
// Package rag provides RAG (Retrieval Augmented Generation) functionality
// for storing and querying documentation in Qdrant vector database.
package rag
import (
"context"
"fmt"
"forge.lthn.ai/core/go/pkg/log"
feat: wire release command, add tar.xz support, unified installers (#277) * feat(cli): wire release command and add installer scripts - Wire up `core build release` subcommand (was orphaned) - Wire up `core monitor` command (missing import in full variant) - Add installer scripts for Unix (.sh) and Windows (.bat) - setup: Interactive with variant selection - ci: Minimal for CI/CD environments - dev: Full development variant - go/php/agent: Targeted development variants - All scripts include security hardening: - Secure temp directories (mktemp -d) - Architecture validation - Version validation after GitHub API call - Proper cleanup on exit - PowerShell PATH updates on Windows (avoids setx truncation) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * feat(build): add tar.xz support and unified installer scripts - Add tar.xz archive support using Borg's compress package - ArchiveXZ() and ArchiveWithFormat() for configurable compression - Better compression ratio than gzip for release artifacts - Consolidate 12 installer scripts into 2 unified scripts - install.sh and install.bat with BunnyCDN edge variable support - Subdomains: setup.core.help, ci.core.help, dev.core.help, etc. - MODE and VARIANT transformed at edge based on subdomain - Installers prefer tar.xz with automatic fallback to tar.gz - Fixed CodeRabbit issues: HTTP status patterns, tar error handling, verify_install params, VARIANT validation, CI PATH persistence Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * chore: add build and release config files - .core/build.yaml - cross-platform build configuration - .core/release.yaml - release workflow configuration Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * chore: move plans from docs/ to tasks/ Consolidate planning documents in tasks/plans/ directory. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(install): address CodeRabbit review feedback - Add curl timeout (--max-time) to prevent hanging on slow networks - Rename TMPDIR to WORK_DIR to avoid clobbering system env var - Add chmod +x to ensure binary has execute permissions - Add error propagation after subroutine calls in batch file - Remove System32 install attempt in CI mode (use consistent INSTALL_DIR) - Fix HTTP status regex for HTTP/2 compatibility Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * feat(rag): add Go RAG implementation with Qdrant + Ollama Add RAG (Retrieval Augmented Generation) tools for storing documentation in Qdrant vector database and querying with semantic search. This replaces the Python tools/rag implementation with a native Go solution. New commands: - core rag ingest [directory] - Ingest markdown files into Qdrant - core rag query [question] - Query vector database with semantic search - core rag collections - List and manage Qdrant collections Features: - Markdown chunking by sections and paragraphs with overlap - UTF-8 safe text handling for international content - Automatic category detection from file paths - Multiple output formats: text, JSON, LLM context injection - Environment variable support for host configuration Dependencies: - github.com/qdrant/go-client (gRPC client) - github.com/ollama/ollama/api (embeddings API) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * feat(deploy): add pure-Go Ansible executor and Coolify API integration Implement infrastructure deployment system with: - pkg/ansible: Pure Go Ansible executor - Playbook/inventory parsing (types.go, parser.go) - Full execution engine with variable templating, loops, blocks, conditionals, handlers, and fact gathering (executor.go) - SSH client with key/password auth and privilege escalation (ssh.go) - 35+ module implementations: shell, command, copy, template, file, apt, service, systemd, user, group, git, docker_compose, etc. (modules.go) - pkg/deploy/coolify: Coolify API client wrapping Python swagger client - List/get servers, projects, applications, databases, services - Generic Call() for any OpenAPI operation - pkg/deploy/python: Embedded Python runtime for swagger client integration - internal/cmd/deploy: CLI commands - core deploy servers/projects/apps/databases/services/team - core deploy call <operation> [params-json] This enables Docker-free infrastructure deployment with Ansible-compatible playbooks executed natively in Go. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(deploy): address linter warnings and build errors - Fix fmt.Sprintf format verb error in ssh.go (remove unused stat command) - Fix errcheck warnings by explicitly ignoring best-effort operations - Fix ineffassign warning in cmd_ansible.go All golangci-lint checks now pass for deploy packages. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * style(deploy): fix gofmt formatting Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(deploy): use known_hosts for SSH host key verification Address CodeQL security alert by using the user's known_hosts file for SSH host key verification when available. Falls back to accepting any key only when known_hosts doesn't exist (common in containerized or ephemeral environments). Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * feat(ai,security,ide): add agentic MVP, security jobs, and Core IDE desktop app Wire up AI infrastructure with unified pkg/ai package (metrics JSONL, RAG integration), move RAG under `core ai rag`, add `core ai metrics` command, and enrich task context with Qdrant documentation. Add `--target` flag to all security commands for external repo scanning, `core security jobs` for distributing findings as GitHub Issues, and consistent error logging across scan/deps/alerts/secrets commands. Add Core IDE Wails v3 desktop app with Angular 20 frontend, MCP bridge (loopback-only HTTP server), WebSocket hub, and Claude Code bridge. Production-ready with Lethean CIC branding, macOS code signing support, and security hardening (origin validation, body size limits, URL scheme checks, memory leak prevention, XSS mitigation). Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix: address PR review comments from CodeRabbit, Copilot, and Gemini Fixes across 25 files addressing 46+ review comments: - pkg/ai/metrics.go: handle error from Close() on writable file handle - pkg/ansible: restore loop vars after loop, restore become settings, fix Upload with become=true and no password (use sudo -n), honour SSH timeout config, use E() helper for contextual errors, quote git refs in checkout commands - pkg/rag: validate chunk config, guard negative-to-uint64 conversion, use E() helper for errors, add context timeout to Ollama HTTP calls - pkg/deploy/python: fix exec.ExitError type assertion (was os.PathError), handle os.UserHomeDir() error - pkg/build/buildcmd: use cmd.Context() instead of context.Background() for proper Ctrl+C cancellation - install.bat: add curl timeouts, CRLF line endings, use --connect-timeout for archive downloads - install.sh: use absolute path for version check in CI mode - tools/rag: fix broken ingest.py function def, escape HTML in query.py, pin qdrant-client version, add markdown code block languages - internal/cmd/rag: add chunk size validation, env override handling Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(build): make release dry-run by default and remove darwin/amd64 target Replace --dry-run (default false) with --we-are-go-for-launch (default false) so `core build release` is safe by default. Remove darwin/amd64 from default build targets (arm64 only for macOS). Fix cmd_project.go to use command context instead of context.Background(). Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-04 00:49:57 +00:00
"github.com/qdrant/go-client/qdrant"
)
// QdrantConfig holds Qdrant connection configuration.
type QdrantConfig struct {
Host string
Port int
APIKey string
UseTLS bool
}
// DefaultQdrantConfig returns default Qdrant configuration.
// Host defaults to localhost for local development.
func DefaultQdrantConfig() QdrantConfig {
return QdrantConfig{
Host: "localhost",
Port: 6334, // gRPC port
UseTLS: false,
}
}
// QdrantClient wraps the Qdrant Go client with convenience methods.
type QdrantClient struct {
client *qdrant.Client
config QdrantConfig
}
// NewQdrantClient creates a new Qdrant client.
func NewQdrantClient(cfg QdrantConfig) (*QdrantClient, error) {
addr := fmt.Sprintf("%s:%d", cfg.Host, cfg.Port)
client, err := qdrant.NewClient(&qdrant.Config{
Host: cfg.Host,
Port: cfg.Port,
APIKey: cfg.APIKey,
UseTLS: cfg.UseTLS,
})
if err != nil {
return nil, log.E("rag.Qdrant", fmt.Sprintf("failed to connect to Qdrant at %s", addr), err)
}
return &QdrantClient{
client: client,
config: cfg,
}, nil
}
// Close closes the Qdrant client connection.
func (q *QdrantClient) Close() error {
return q.client.Close()
}
// HealthCheck verifies the connection to Qdrant.
func (q *QdrantClient) HealthCheck(ctx context.Context) error {
_, err := q.client.HealthCheck(ctx)
return err
}
// ListCollections returns all collection names.
func (q *QdrantClient) ListCollections(ctx context.Context) ([]string, error) {
resp, err := q.client.ListCollections(ctx)
if err != nil {
return nil, err
}
names := make([]string, len(resp))
copy(names, resp)
return names, nil
}
// CollectionExists checks if a collection exists.
func (q *QdrantClient) CollectionExists(ctx context.Context, name string) (bool, error) {
return q.client.CollectionExists(ctx, name)
}
// CreateCollection creates a new collection with cosine distance.
func (q *QdrantClient) CreateCollection(ctx context.Context, name string, vectorSize uint64) error {
return q.client.CreateCollection(ctx, &qdrant.CreateCollection{
CollectionName: name,
VectorsConfig: qdrant.NewVectorsConfig(&qdrant.VectorParams{
Size: vectorSize,
Distance: qdrant.Distance_Cosine,
}),
})
}
// DeleteCollection deletes a collection.
func (q *QdrantClient) DeleteCollection(ctx context.Context, name string) error {
return q.client.DeleteCollection(ctx, name)
}
// CollectionInfo returns information about a collection.
func (q *QdrantClient) CollectionInfo(ctx context.Context, name string) (*qdrant.CollectionInfo, error) {
return q.client.GetCollectionInfo(ctx, name)
}
// Point represents a vector point with payload.
type Point struct {
ID string
Vector []float32
Payload map[string]any
}
// UpsertPoints inserts or updates points in a collection.
func (q *QdrantClient) UpsertPoints(ctx context.Context, collection string, points []Point) error {
if len(points) == 0 {
return nil
}
qdrantPoints := make([]*qdrant.PointStruct, len(points))
for i, p := range points {
qdrantPoints[i] = &qdrant.PointStruct{
Id: qdrant.NewID(p.ID),
Vectors: qdrant.NewVectors(p.Vector...),
Payload: qdrant.NewValueMap(p.Payload),
}
}
_, err := q.client.Upsert(ctx, &qdrant.UpsertPoints{
CollectionName: collection,
Points: qdrantPoints,
})
return err
}
// SearchResult represents a search result with score.
type SearchResult struct {
ID string
Score float32
Payload map[string]any
}
// Search performs a vector similarity search.
func (q *QdrantClient) Search(ctx context.Context, collection string, vector []float32, limit uint64, filter map[string]string) ([]SearchResult, error) {
query := &qdrant.QueryPoints{
CollectionName: collection,
Query: qdrant.NewQuery(vector...),
Limit: qdrant.PtrOf(limit),
WithPayload: qdrant.NewWithPayload(true),
}
// Add filter if provided
if len(filter) > 0 {
conditions := make([]*qdrant.Condition, 0, len(filter))
for k, v := range filter {
conditions = append(conditions, qdrant.NewMatch(k, v))
}
query.Filter = &qdrant.Filter{
Must: conditions,
}
}
resp, err := q.client.Query(ctx, query)
if err != nil {
return nil, err
}
results := make([]SearchResult, len(resp))
for i, p := range resp {
payload := make(map[string]any)
for k, v := range p.Payload {
payload[k] = valueToGo(v)
}
results[i] = SearchResult{
ID: pointIDToString(p.Id),
Score: p.Score,
Payload: payload,
}
}
return results, nil
}
// pointIDToString converts a Qdrant point ID to string.
func pointIDToString(id *qdrant.PointId) string {
if id == nil {
return ""
}
switch v := id.PointIdOptions.(type) {
case *qdrant.PointId_Num:
return fmt.Sprintf("%d", v.Num)
case *qdrant.PointId_Uuid:
return v.Uuid
default:
return ""
}
}
// valueToGo converts a Qdrant value to a Go value.
func valueToGo(v *qdrant.Value) any {
if v == nil {
return nil
}
switch val := v.Kind.(type) {
case *qdrant.Value_StringValue:
return val.StringValue
case *qdrant.Value_IntegerValue:
return val.IntegerValue
case *qdrant.Value_DoubleValue:
return val.DoubleValue
case *qdrant.Value_BoolValue:
return val.BoolValue
case *qdrant.Value_ListValue:
list := make([]any, len(val.ListValue.Values))
for i, item := range val.ListValue.Values {
list[i] = valueToGo(item)
}
return list
case *qdrant.Value_StructValue:
m := make(map[string]any)
for k, item := range val.StructValue.Fields {
m[k] = valueToGo(item)
}
return m
default:
return nil
}
}