hermes 外部记忆openviking服务端切换为本地Ollama模型

环境Win11WSL2Ubuntu24.04openviking-server --versionopenviking-server 0.4.10ov --helpOpenViking v0.4.11.dev0一、相关文档记忆提供程序Memory Providersopenviking简介openviking快速开始在线服务OpenViking Service火山引擎云产品介绍二、备份数据停止服务CtrlC 或pkill -f openviking-server备份数据目录cp -r ~/.openviking/data ~/.openviking/data_backup_volc_embedding三、切换vlm模型VLM视觉语言模型doubao-seed-2-0-lite面向企业规模化部署的轻量级全模态模型支持文本、图片、语音、视频四模态跨模态联合理解。集成音画协同分析、长视频时序检索、全维度音频解析、代码开发、智能Agent与GUI闭环操作能力适配大批量全模态推理业务场景。输入文本、图片、视频、音频qwen3.6:27bQwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.vision tools thinking 27b 35bqwen3.6:35bQwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.vision tools thinking 27b 35b与前代 Qwen 模型相比Qwen3.6 在智能体编码能力和思维链上下文保留两方面有大幅升级具备视觉理解、工具调用、深度推理三大核心特性提供 27B、35B 两个参数版本。openviking-server init操作uadminUD26:~$ openviking-server init ╭─────────────────────────────────────────────────────────╮ │ OpenViking Setup │ │ Context database for AI agents — data in, context out │ ╰─────────────────────────────────────────────────────────╯ Data will be stored under /home/uadmin/.openviking/data unless you edit ov.conf later. Existing config found: /home/uadmin/.openviking/ov.conf Current configuration Embedding: openai · text-embedding-v4 (1024d) VLM: openai · qwen3.6-flash Query planner: litellm · ollama/guoxuter/ov_intent_analysis_sft:v7_q8 Server: 127.0.0.1:1933 · auth dev (no auth) What would you like to do? ↑/↓ move · enter select ❯ Start over (full setup, current config backed up as .bak) Update VLM (now: openai · qwen3.6-flash) Update embedding (now: openai · text-embedding-v4 (1024d)) Update server auth (now: 127.0.0.1:1933 · auth dev (no auth)) Cancel 选Update VLM --------------------------------------------------------------------------------------- ❯ Update VLM Current VLM: openai · qwen3.6-flash VLM provider: ↑/↓ move · enter select VolcEngine (火山引擎) (API) BytePlus (API) OpenAI (API) OpenAI Codex (Subscription) Kimi (Subscription API Key) GLM (Subscription API Key) ❯ Custom (OpenAI-compatible) (Any OpenAI-compatible endpoint) Local via Ollama (no API key, runs on this machine) 选Local via Ollama --------------------------------------------------------------------------------------- ❯ Local via Ollama Checking Ollama... not installed Install Ollama now? [Y/n]: 输入n --------------------------------------------------------------------------------------- Install Ollama now? [Y/n]: n Manual install: https://ollama.com/download Continue without Ollama? [y/N]: 输入y --------------------------------------------------------------------------------------- Continue without Ollama? [y/N]: y Vision-language model (VLM) — parses documents images: ↑/↓ move · enter select · ← back Qwen 3.5 4B (~3.4 GB) Qwen 3.5 9B (~6.6 GB) Qwen 3.6 27B (~17 GB, 256K ctx) Qwen 3.6 35B (~24 GB, 256K ctx) Qwen 3.5 122B (~81 GB) Gemma 4 E2B (~7.2 GB) ❯ Gemma 4 E4B (~9.6 GB) * Gemma 4 26B (~18 GB) Gemma 4 31B (~20 GB) 选Qwen 3.6 35B --------------------------------------------------------------------------------------- ❯ Qwen 3.6 35B Change: openai · qwen3.6-flash → litellm · ollama/qwen3.6:35b Save configuration? [Y/n]: --------------------------------------------------------------------------------------- Save configuration? [Y/n]: Y Existing config backed up to /home/uadmin/.openviking/ov.conf.bak.1 OK Configuration updated Validate the setup now? (runs openviking-server doctor) [Y/n]: --------------------------------------------------------------------------------------- Validate the setup now? (runs openviking-server doctor) [Y/n]: Y OpenViking Doctor Config: PASS /home/uadmin/.openviking/ov.conf Python: PASS 3.11.15 ( 3.10 required) Native Engine: PASS variantx86_avx2 AGFS: PASS AGFS SDK 0.1.7 Embedding: PASS openai/text-embedding-v4 api_basehttps://dashscope.aliyuncs.com/compatible-mode/v1 dimension1024 probe ok (dimension1024) VLM: PASS litellm/ollama/qwen3.6:35b Ollama: PASS running at localhost:11434 VikingBot: PASS VikingBot aligned with dev OpenViking auth Disk: PASS 948.3 GB free in /home/uadmin/.openviking/data All checks passed. Start the server now? [y/N]: --------------------------------------------------------------------------------------- Start the server now? [y/N]: Nopenviking-server init操作日志uadminUD26:~$ openviking-server init ╭─────────────────────────────────────────────────────────╮ │ OpenViking Setup │ │ Context database for AI agents — data in, context out │ ╰─────────────────────────────────────────────────────────╯ Data will be stored under /home/uadmin/.openviking/data unless you edit ov.conf later. Existing config found: /home/uadmin/.openviking/ov.conf Current configuration Embedding: openai · text-embedding-v4 (1024d) VLM: openai · qwen3.6-flash Query planner: litellm · ollama/guoxuter/ov_intent_analysis_sft:v7_q8 Server: 127.0.0.1:1933 · auth dev (no auth) What would you like to do? ↑/↓ move · enter select ❯ Update VLM Current VLM: openai · qwen3.6-flash VLM provider: ↑/↓ move · enter select ❯ Local via Ollama Checking Ollama... not installed Install Ollama now? [Y/n]: n Manual install: https://ollama.com/download Continue without Ollama? [y/N]: y Vision-language model (VLM) — parses documents images: ↑/↓ move · enter select · ← back ❯ Qwen 3.6 35B Change: openai · qwen3.6-flash → litellm · ollama/qwen3.6:35b Save configuration? [Y/n]: Y Existing config backed up to /home/uadmin/.openviking/ov.conf.bak.1 OK Configuration updated Validate the setup now? (runs openviking-server doctor) [Y/n]: Y OpenViking Doctor Config: PASS /home/uadmin/.openviking/ov.conf Python: PASS 3.11.15 ( 3.10 required) Native Engine: PASS variantx86_avx2 AGFS: PASS AGFS SDK 0.1.7 Embedding: PASS openai/text-embedding-v4 api_basehttps://dashscope.aliyuncs.com/compatible-mode/v1 dimension1024 probe ok (dimension1024) VLM: PASS litellm/ollama/qwen3.6:35b Ollama: PASS running at localhost:11434 VikingBot: PASS VikingBot aligned with dev OpenViking auth Disk: PASS 948.3 GB free in /home/uadmin/.openviking/data All checks passed. Start the server now? [y/N]: N配置文件ov.conf~/.openviking/ov.confvlm: { provider: litellm, model: ollama/qwen3.6:35b, api_key: no-key, api_base: http://localhost:11434, temperature: 0.0, max_retries: 2, extra_request_body: { num_ctx: 16384, think: false } },关于num_ctx: 16384,think: false场景定位决定不需要超长上下文后续看需求酌情加大VLM 是工具型角色不需要深度推理四、切换embedding模型openviking-server init操作uadminUD26:~$ openviking-server init ╭─────────────────────────────────────────────────────────╮ │ OpenViking Setup │ │ Context database for AI agents — data in, context out │ ╰─────────────────────────────────────────────────────────╯ Data will be stored under /home/uadmin/.openviking/data unless you edit ov.conf later. Existing config found: /home/uadmin/.openviking/ov.conf Current configuration Embedding: openai · text-embedding-v4 (1024d) VLM: litellm · ollama/qwen3.6:35b Query planner: litellm · ollama/guoxuter/ov_intent_analysis_sft:v7_q8 Server: 127.0.0.1:1933 · auth dev (no auth) What would you like to do? ↑/↓ move · enter select ❯ Start over (full setup, current config backed up as .bak) Update VLM (now: litellm · ollama/qwen3.6:35b) Update embedding (now: openai · text-embedding-v4 (1024d)) Update server auth (now: 127.0.0.1:1933 · auth dev (no auth)) Cancel 选Update embedding --------------------------------------------------------------------------------------- ❯ Update embedding Current embedding: openai · text-embedding-v4 (1024d) Embedding setup: ↑/↓ move · enter select ❯ Cloud API (VolcEngine, BytePlus, OpenAI) Local via Ollama (no API key, runs on this machine) Lightweight CPU embedding (llama.cpp, ~24 MB, no Ollama needed) 选Local via Ollama --------------------------------------------------------------------------------------- ❯ Local via Ollama Checking Ollama... not installed Install Ollama now? [Y/n]: 输入n --------------------------------------------------------------------------------------- Install Ollama now? [Y/n]: n Manual install: https://ollama.com/download Continue without Ollama? [y/N]: 输入y --------------------------------------------------------------------------------------- Embedding model — powers semantic search: ↑/↓ move · enter select · ← back Qwen3-Embedding 0.6B (1024d, ~639 MB) Qwen3-Embedding 4B (1024d, ~2.5 GB) ❯ Qwen3-Embedding 8B (1024d, ~4.7 GB) * EmbeddingGemma 300M (768d, ~622 MB) 选择Qwen3-Embedding 0.6B --------------------------------------------------------------------------------------- ❯ Qwen3-Embedding 0.6B Change: openai · text-embedding-v4 (1024d) → ollama · qwen3-embedding:0.6b (1024d) Save configuration? [Y/n]: 输入Y --------------------------------------------------------------------------------------- Save configuration? [Y/n]: Y Existing config backed up to /home/uadmin/.openviking/ov.conf.bak.2 OK Configuration updated Validate the setup now? (runs openviking-server doctor) [Y/n]: 输入Y --------------------------------------------------------------------------------------- Validate the setup now? (runs openviking-server doctor) [Y/n]: Y OpenViking Doctor Config: PASS /home/uadmin/.openviking/ov.conf Python: PASS 3.11.15 ( 3.10 required) Native Engine: PASS variantx86_avx2 AGFS: PASS AGFS SDK 0.1.7 08:05:58 - LiteLLM:WARNING: get_model_cost_map.py:264 - LiteLLM: Failed to fetch remote model cost map from https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json: The read operation timed out. Falling back to local backup. Embedding: PASS ollama/qwen3-embedding:0.6b api_basehttp://localhost:11434/v1 dimension1024 probe ok (dimension1024) VLM: PASS litellm/ollama/qwen3.6:35b Ollama: PASS running at localhost:11434 VikingBot: PASS VikingBot aligned with dev OpenViking auth Disk: PASS 948.3 GB free in /home/uadmin/.openviking/data All checks passed. Start the server now? [y/N]: 输入N --------------------------------------------------------------------------------------- Start the server now? [y/N]: N --------------------------------------------------------------------------------------- 这个警告可以忽略。 LiteLLM 在初始化时会默认尝试从 GitHub 远程拉取一份 model_prices_and_context_window.json 文件这份文件的作用是 记录各云端 API 模型的 token 单价用于计费、成本统计 补充部分模型的上下文窗口、参数元数据。 --------------------------------------------------------------------------------------- 再次执行就好了 uadminUD26:~$ openviking-server doctor OpenViking Doctor Config: PASS /home/uadmin/.openviking/ov.conf Python: PASS 3.11.15 ( 3.10 required) Native Engine: PASS variantx86_avx2 AGFS: PASS AGFS SDK 0.1.7 Embedding: PASS ollama/qwen3-embedding:0.6b api_basehttp://localhost:11434/v1 dimension1024 probe ok (dimension1024) VLM: PASS litellm/ollama/qwen3.6:35b Ollama: PASS running at localhost:11434 VikingBot: PASS VikingBot aligned with dev OpenViking auth Disk: PASS 948.3 GB free in /home/uadmin/.openviking/data All checks passed.openviking-server init操作日志uadminUD26:~$ openviking-server init ╭─────────────────────────────────────────────────────────╮ │ OpenViking Setup │ │ Context database for AI agents — data in, context out │ ╰─────────────────────────────────────────────────────────╯ Data will be stored under /home/uadmin/.openviking/data unless you edit ov.conf later. Existing config found: /home/uadmin/.openviking/ov.conf Current configuration Embedding: openai · text-embedding-v4 (1024d) VLM: litellm · ollama/qwen3.6:35b Query planner: litellm · ollama/guoxuter/ov_intent_analysis_sft:v7_q8 Server: 127.0.0.1:1933 · auth dev (no auth) What would you like to do? ↑/↓ move · enter select ❯ Update embedding Current embedding: openai · text-embedding-v4 (1024d) Embedding setup: ↑/↓ move · enter select ❯ Local via Ollama Checking Ollama... not installed Install Ollama now? [Y/n]: n Manual install: https://ollama.com/download Continue without Ollama? [y/N]: y Embedding model — powers semantic search: ↑/↓ move · enter select · ← back ❯ Qwen3-Embedding 0.6B Change: openai · text-embedding-v4 (1024d) → ollama · qwen3-embedding:0.6b (1024d) Save configuration? [Y/n]: Y Existing config backed up to /home/uadmin/.openviking/ov.conf.bak.3 OK Configuration updated Validate the setup now? (runs openviking-server doctor) [Y/n]: Y OpenViking Doctor Config: PASS /home/uadmin/.openviking/ov.conf Python: PASS 3.11.15 ( 3.10 required) Native Engine: PASS variantx86_avx2 AGFS: PASS AGFS SDK 0.1.7 08:38:37 - LiteLLM:WARNING: get_model_cost_map.py:264 - LiteLLM: Failed to fetch remote model cost map from https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json: The read operation timed out. Falling back to local backup. Embedding: PASS ollama/qwen3-embedding:0.6b api_basehttp://localhost:11434/v1 dimension1024 probe ok (dimension1024) VLM: PASS litellm/ollama/qwen3.6:35b Ollama: PASS running at localhost:11434 VikingBot: PASS VikingBot aligned with dev OpenViking auth Disk: PASS 948.3 GB free in /home/uadmin/.openviking/data All checks passed. Start the server now? [y/N]: N --------------------------------------------------------------------------------------- 再次执行就好了 uadminUD26:~$ openviking-server doctor OpenViking Doctor Config: PASS /home/uadmin/.openviking/ov.conf Python: PASS 3.11.15 ( 3.10 required) Native Engine: PASS variantx86_avx2 AGFS: PASS AGFS SDK 0.1.7 Embedding: PASS ollama/qwen3-embedding:0.6b api_basehttp://localhost:11434/v1 dimension1024 probe ok (dimension1024) VLM: PASS litellm/ollama/qwen3.6:35b Ollama: PASS running at localhost:11434 VikingBot: PASS VikingBot aligned with dev OpenViking auth Disk: PASS 948.3 GB free in /home/uadmin/.openviking/data All checks passed.配置文件ov.conf~/.openviking/ov.conf~/.openviking/ov.conf embedding: { dense: { provider: ollama, model: qwen3-embedding:0.6b, api_base: http://localhost:11434/v1, dimension: 1024, input: text } },更换嵌入模型后向量数据需要处理。如果是少量测试数据可以清理了。如果想保留数据可以重建向量数据。五、清理向量数据停止服务CtrlC 或pkill -f openviking-server备份数据目录cp -r ~/.openviking/data ~/.openviking/data_backup_volc_embedding删除目录rm -rf ~/.openviking/data/*#mv ~/.openviking/data ~/.openviking/data1重启服务会生成data目录openviking-server六、处理向量数据启动服务openviking-server日志报错openviking.storage.errors.EmbeddingRebuildRequiredError: Existing collection embedding metadata does not match current configuration. Rebuild is required before using the current embedding model, or set embedding.allow_metadata_overridetrue to keep existing vectors when only provider/model changed (dimension must remain the same).------------------------------------2026-07-26 08:42:11,110 - uvicorn.error - ERROR - Application startup failed. Exiting.修改配置文件ov.conf~/.openviking/ov.conf在embedding下加入allow_metadata_override: true~/.openviking/ov.conf embedding: { dense: { provider: ollama, model: qwen3-embedding:0.6b, api_base: http://localhost:11434/v1, dimension: 1024, input: text }, allow_metadata_override: true },再次启动服务openviking-server日志提示2026-07-26 08:43:55,232 - openviking.storage.collection_schemas - WARNING - Embedding metadata changed (provider/model) but dimension is unchanged; embedding.allow_metadata_overridetrue, so the existing collection metadata will be rewritten and existing vectors kept. old{dimension: 1024, model: text-embedding-v4, model_identity: text-embedding-v4, provider: openai} new{provider: ollama, model: qwen3-embedding:0.6b, dimension: 1024, model_identity: qwen3-embedding:0.6b}重建向量数据看根目录有什么ov ls viking:///uadminUD26:~$ ov ls viking:/// cmd: ov ls viking:/// -l 256 -n 256 1. dir · 2026-07-26 01:05 viking://resources 本目录构成了 **Hermes Agent 框架** 的核心技术文档体系专注于指导开发者构建、配置及优化具备跨会话持久化记忆能力的智能代理系统。... 2. dir · 2026-07-26 01:08 viking://user The user directory serves as a foundational component within a sophisticated, multi-agent AI assistant framework.# 1. 重建全局资源库的向量手动导入的文档、素材、公共资源ov reindex viking://resources/ --mode vectors_only --wait true# 2. 重建默认用户的所有对话记忆与个人数据的向量ov reindex viking://user/default/ --mode vectors_only --wait trueuadminUD26:~$ ov reindex viking://resources/ --mode vectors_only --wait true status completed uri viking://resources object_type resource mode vectors_only scanned_records 12 rebuilt_records 17 deleted_records 0 would_delete_records 0 unsupported_records 0 failed_records 0 duration_ms 3035 warnings [] uadminUD26:~$ ov reindex viking://user/default/ --mode vectors_only --wait true status completed uri viking://user/default object_type user_namespace mode vectors_only scanned_records 34 rebuilt_records 36 deleted_records 0 would_delete_records 0 unsupported_records 0 failed_records 0 duration_ms 5087 warnings []测试ov find 测试标记uadminUD26:~$ ov find 测试标记 cmd: ov find --uri -n 10 测试标记 10 results Ranked by relevance · limit 10 final results 1. memory · Level 2 · score 0.556 viking://user/default/memories/preferences/2026/07/24/凌晨开发_openviking-20260724.md 测试标记为 openviking-20260724开发者凌晨仍在开发中。 2. memory · Level 2 · score 0.441 viking://user/default/memories/cases/viking记忆保存与搜索验证.md # viking记忆保存与搜索验证 ## Task Signature 用户保存开发环境相关事实后执行语义搜索验证记忆可被正确检索再浏览viking根目录确认仓库结构... 3. memory · Level 1 · score 0.438 viking://user/default/memories/cases/.overview.md No abstract available ...ov find --help重新生成语义摘要和重建向量索引一般重建向量数据即可不用重建语义摘要。# 1. 全局资源库重新生成语义摘要 重建向量索引ov reindex viking://resources/ --mode semantic_and_vectors --wait true# 2. 默认用户记忆库重新生成语义摘要 重建向量索引ov reindex viking://user/default/ --mode semantic_and_vectors --wait true命令执行报错uadminUD26:~$ ov reindex viking://resources/ --mode semantic_and_vectors --wait true ov reindex viking://resources/ --mode semantic_and_vectors --wait true ╭─ Connection Error ───────────────────────────────────────────────────╮ │ Could not reach OpenViking. The server may be offline, or this │ │ config points to the wrong URL. │ ╰──────────────────────────────────────────────────────────────────────╯ Next: ov config validate Check the active config ov health Run a quick server health check ov config switch Switch to another config # 这句命令更容易报错 uadminUD26:~$ ov reindex viking://user/default/ --mode semantic_and_vectors ov reindex viking://user/default/ --mode semantic_and_vectors ╭─ Connection Error ───────────────────────────────────────────────────╮ │ Could not reach OpenViking. The server may be offline, or this │ │ config points to the wrong URL. │ ╰──────────────────────────────────────────────────────────────────────╯ Next: ov config validate Check the active config ov health Run a quick server health check ov config switch Switch to another configopenviking-server日志报错2026-07-26 10:04:27,750 - openviking.models.embedder.openai_embedders - WARNING - OpenAI async embedding slow call providerollama modelqwen3-embedding:0.6b wait_ms0.00 duration_ms17759.37 2026-07-26 10:04:38,832 - openviking.models.embedder.openai_embedders - WARNING - OpenAI async embedding slow call providerollama modelqwen3-embedding:0.6b wait_ms0.00 duration_ms10156.07 2026-07-26 10:05:15,026 - openviking.models.embedder.openai_embedders - WARNING - OpenAI async embedding slow call providerollama modelqwen3-embedding:0.6b wait_ms0.00 duration_ms6433.25 [07/26/26 10:05:13] INFO utils.py:3799 LiteLLM completion() model qwen3.6:35b; provider ollama ERROR Task was destroyed but it is pending! base_events.py:1785 task: Task pending nameTask-381 coroLoggingWorker._worker_loop() running at /home/uadmin/.local/share/uv/tools/openviking/lib/python3.11/site-packages/litellm/litellm_core_utils/logging_worker.py:120 wait_forFuture pending cb[Task.task_wakeup()]问题分析可能是Ollama压力稍大处理不过来调整配置Ollma环境变量# 允许同时处理 2 个推理请求VLM 与嵌入任务并行执行避免完全串行排队OLLAMA_NUM_PARALLEL2# 允许 2 个模型同时常驻显存避免 VLM 和嵌入模型来回加载卸载OLLAMA_MAX_LOADED_MODELS2# 开启 FlashAttention 硬件加速降低显存占用、提升推理速度OLLAMA_FLASH_ATTENTION1ollama serve重启Ollama启动日志能看见这个几个变量测试Ollama可是在一个窗口发送命令ollama run qwen3.6:35b 写一篇1000字的人工智能科普文章 后再开新窗口同时执行PowerShellcurl -Method Post -Uri http://localhost:11434/api/embeddings -ContentType application/json -Body {model: qwen3-embedding:0.6b, prompt: 测试文本} -UseBasicParsing#curl.exe --% -X POST http://localhost:11434/api/embeddings -H Content-Type: application/json -d {\model\: \qwen3-embedding:0.6b\, \prompt\: \测试文本\}查看执行时间PowerShellMeasure-Command { curl -Method Post -Uri http://localhost:11434/api/embeddings -ContentType application/json -Body {model: qwen3-embedding-cpu:0.6b, prompt: 测试文本} -UseBasicParsing }ov.conf配置vlm模型从num_ctx: 16384改到8192重启服务后来又改回去了嵌入模型调整嵌入模型改为qwen3-embedding-cpu:0.6b自定义模型需要制作简单再次执行uadminUD26:~$ ov reindex viking://resources/ --mode semantic_and_vectors --wait true status completed uri viking://resources object_type resource mode semantic_and_vectors scanned_records 12 rebuilt_records 17 deleted_records 0 would_delete_records 0 unsupported_records 0 failed_records 0 duration_ms 51108 warnings [] uadminUD26:~$ ov reindex viking://user/default/ --mode semantic_and_vectors status completed uri viking://user/default object_type user_namespace mode semantic_and_vectors scanned_records 34 rebuilt_records 36 deleted_records 0 would_delete_records 0 unsupported_records 0 failed_records 0 duration_ms 59424 warnings []如果openviking-server日志里有报错ov命令执行成了可以接受。测试ov finduadminUD26:~$ ov find 测试标记 -u viking://user/default cmd: ov find --uriviking://user/default -n 10 测试标记 10 results Ranked by relevance · limit 10 final results 1. memory · Level 2 · score 0.556 viking://user/default/memories/preferences/2026/07/24/凌晨开发_openviking-20260724.md 测试标记为 openviking-20260724开发者凌晨仍在开发中。 2. memory · Level 2 · score 0.443 viking://user/default/memories/cases/viking记忆保存与搜索验证.md # viking记忆保存与搜索验证 ## Task Signature 用户保存开发环境相关事实后执行语义搜索验证记忆可被正确检索再浏览viking根目录确认仓库结构... 3. memory · Level 1 · score 0.438 viking://user/default/memories/cases/.overview.md No abstract available.修改配置文件ov.conf~/.openviking/ov.conf在embedding下去掉allow_metadata_override: true重启openviking服务