iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
You can set up local semantic code search in Zoo Code using Ollama’s BGE-M3 embeddings and Qdrant. The documented workflow parses code into blocks, embeds them, stores vectors, and makes them searchable with natural-language queries. There is no published end-to-end benchmark establishing that this setup is “lightning-fast” on arbitrary hardware, and the instructions below are specifically verified for Zoo Code—not for every Roo Code release or current Cline builds.
How the indexing pipeline works
Zoo Code’s indexing guide describes a four-part flow: Tree-sitter parses supported source files into blocks such as functions, classes, and methods; an embedding provider turns those blocks into vectors; Qdrant stores the vectors; and Zoo Code exposes a codebase_search tool to retrieve relevant code for a natural-language question. Zoo Code describes the feature as creating a semantic search index using AI embeddings. See the Zoo Code codebase-indexing guide.
This is semantic retrieval, not a replacement for exact text search. It is useful for questions such as “How is user authentication handled?” or “Where are API endpoints defined?” when you know what you want to find but not the relevant file or identifier.
Recommended Free Tools
What you need
- Zoo Code with its codebase-indexing feature.
- Docker for the documented local Qdrant setup, or a Qdrant cloud deployment and its endpoint credentials.
- Ollama running locally, with the BGE-M3 model pulled.
- A repository whose relevant files can be parsed. Zoo Code says Tree-sitter-supported languages produce the best results.
The documentation gives no minimum hardware specification. Indexing time depends on the repository, file filtering, local compute, model loading, and database location; those factors are not a published speed benchmark.
#1 Best Overall
- V-COOLING — A MORE ADVANCED ALTERNATIVE TO DUAL HEAT PIPES — The VZMORE AX9 Max mini computers features V-Cooling, replacing conventional dual heat pipes with a large-area VC vapor chamber for faster, more even heat dissipation. Compared with conventional dual heat pipes, the design increases heat-spreading area by 40% and improves heat-transfer efficiency by 50%, helping reduce local hot spots under heavy loads. With 360° bottom air intake, vertical airflow, high-density cooling fins, and intelligent fan control, it helps sustain strong performance while keeping thermals and noise under control.
- V-BOOST PRO WITH UP TO 65W PERFORMANCE HEADROOM — V-Boost Pro gives the AX9 Max mini gaming PC three tuned operating modes: 45W Silent Mode, 54W Normal Mode, and 65W Performance Mode. Choose quieter acoustics, balanced everyday use, or stronger sustained performance for creative and compute-intensive workloads. Working with V-Cooling, V-Boost Pro helps translate available thermal capacity into stable, controlled performance.
- AMD RYZEN AI 9 HX 470 + RADEON 890M GRAPHICS — Powered by AMD Ryzen AI 9 HX 470 with 12 cores, 24 threads, and boost clocks up to 5.2GHz, the VZMORE AX9 Max Ryzen mini PC delivers powerful performance for professional multitasking, software development, content creation, rendering, and encoding. Radeon 890M graphics with RDNA 3.5 architecture support high-resolution media, creative applications, and 1080p gaming in supported titles, bringing work and entertainment together in a compact desktop.
- AI MINI PC BUILT FOR LOCAL AI — Bring AI to your desktop with the VZMORE AX9 Max, an AI mini PC with NPU and up to 86 TOPS of overall AI performance. Designed for local AI workflows, it supports tools such as LM Studio, Ollama, and AMD GAIA for running compatible Qwen, Llama, Gemma, and DeepSeek models locally. Local processing helps keep sensitive data on your device and reduces reliance on cloud-based AI services.
- ENGINEERED FOR LONG-TERM RELIABILITY + 3-YEAR PRODUCT SUPPORT — The VZMORE AX9 Max mini desktop computer combines a durable chassis with an optimized air-intake design for efficient cooling and long-term stability. VZMORE micro pc undergo extensive testing for sustained workloads, thermal balance, acoustics, power stability, port durability, multi-display compatibility, network reliability, memory and storage integrity, and system stability. Backed by a 3-year product support and 24/7 customer support, AX9 Max delivers dependable performance for everyday use.
Set up Qdrant and BGE-M3
1. Start a local Qdrant instance
For a local database, Zoo Code’s guide provides this Docker command. It publishes Qdrant’s port 6333 and keeps its storage in the named volume qdrant_data:
docker run -d
--name qdrant
--restart unless-stopped
-p 6333:6333
-v qdrant_data:/qdrant/storage
qdrant/qdrantThe local endpoint to enter in Zoo Code is http://localhost:6333. If you use a cloud Qdrant deployment instead, enter that deployment’s endpoint and provide its API key if required. The choice changes where vectors are stored: local Qdrant keeps them on your machine, while a cloud endpoint stores them with that service. The Qdrant documentation explains the database and its vector-search concepts.
Rank #2
- 【AMD Ryzen 4300U True 4-Core CPU: Outperforms N95 & i3-10110U】KAMRUI P2 Mini PC is equipped with true 4-core AMD Ryzen 4300U processor built on advanced 7nm Zen2 architecture，This means you get consistent, unthrottled performance for hours on end, whether you’re running multiple browser tabs, streaming 4K content, or managing virtual machines. Compare that to Intel N95 (4 efficiency cores that throttle under load) or Intel i3-10110U (only 2 cores total), and the difference is night and day: The KAMRUI P2 AMD Ryzen 4300U (28W) is 40% faster than the Intel i3-10110U and 25% faster than the Intel N95 in multi-core tasks, ensuring smooth, lag-free performance even during heavy workloads.
- 【Integrated AMD Radeon Graphics: 2.5X Stronger for Tri 4K】The KAMRUI P2 AMD 4300U Mini PC have unlocked the full potential of the built-in AMD Radeon Vega 5 graphics with 28W power delivery, making it 2.5 times stronger than the Intel UHD graphics found in the N95 and i3-10110U. This means you can enjoy Tri 4K@60Hz displays without a single stutter, perfect for productivity setups, home theaters, or even light photo/video editing and casual gaming. While the Intel N95/i3-10110U struggle to run a single 4K display without lag, The KAMRUI AMD 4300U Mini PC handles Tri 4K effortlessly, turning your workspace into a high-efficiency hub or your living room into a premium entertainment center.
- 【Large Storage Capacity, Easy Expansion】KAMRUI Pinova P2 mini computers is equipped with 16GB LPDDR4 for faster multitasking and smooth application switching. 512GB M.2 SSD ensures fast startup, fast file transfers and plenty of storage space,eliminating slow loading times and ensuring fast responsiveness. the two storage slots (1x M.2 2280 SATA/NVMe PCIe3.0 slot, 1x M.2 2280 SATA slot) can be combined to provide up to 4TB of total storage(Not included). This gives you enough space for all your projects, media and data.
- 【4K Triple Display】KAMRUI Pinova P2 4300U mini desktop computers is equipped with HDMI2.0 ×1 +DP1.4 ×1+USB3.2 Gen2 Type-C ×1 interfaces for faster transmission, Triple 4K@60Hz Display, KAMRUI P2 mini computer is ideal for visual home entertainment, home office, conference rooms, etc. USB3.2 Gen2 Type-A port ×2 with a transfer speed of up to 10 Gbps (21 times faster than USB 2.0) for efficient data transfer. Ideal for seamless multitasking between spreadsheets, browsers and presentations, or for an immersive entertainment experience.
- 【USB3.2 Gen2 Type-C 10Gbps, Versatile connectivity】KAMRUI P2 mini desktop pc fast and versatile connectivity! The USB3.2 Gen2 Type-C port offers a data transfer rate of 10Gbps and simultaneously supports DisplayPort 1.4 video output. The P2 AMD Ryzen 4300U Mini PC is complemented by Gigabit LAN, WiFi and Bluetooth, so nothing stands in the way of a productive working environment.
2. Pull BGE-M3 in Ollama
Run the model pull command in a terminal:
ollama pull bge-m3Ollama’s model listing documents BGE-M3 and its embedding API. For a typical local Ollama installation, the base URL is http://localhost:11434. The listing reports a 1.2 GB default model package, an 8K context window, and 1024 embedding dimensions; package size and context capacity are not speed estimates or hardware requirements. See Ollama’s BGE-M3 listing.
Configure Zoo Code and start indexing
- Open Zoo Code’s codebase-indexing panel.
- Choose
Ollamaas the embedding provider. - Set the Ollama base URL to
http://localhost:11434and choosebge-m3. - Enter the Qdrant URL:
http://localhost:6333for the local Docker instance, or your cloud endpoint. Add a Qdrant API key only if your deployment requires one. - Save the settings and start indexing. The panel reports indexing, indexed, and error states.
Zoo Code’s guide says parsing happens locally, respects file permissions and ignore patterns, and sends code chunks of 100–1000 characters to the embedding provider. It says vectors remain in the selected Qdrant instance and describes Ollama with local Qdrant as an offline option. These are the vendor’s documented privacy and data-flow claims, not independently verified network measurements. A cloud Qdrant deployment means vectors are stored remotely.
Rank #3
- Supercomputer performance directly to your desk in a compact, energy-efficient design, enabling enterprise-scale AI and high-performance computing right where you need it.
- The power of Grace Blackwell architecture, delivering up to 1 petaFLOP of AI performance for local model fine-tuning, inference, and analytics, accelerating your time-to-solution.
- Designed from the ground up to build and run AI, delivering seamless integration of the full NVIDIA AI software stack —so you can develop locally and deploy anywhere.
- NVIDIA DGX Spark gives you the freedom to experiment, prototype, and innovate faster by augmenting laptop, desktop, cloud, or data center resources. With more power to learn, prototype, test, and innovate, NVIDIA DGX Spark delivers exceptional ROI for increased productivity.
- Use NVIDIA DGX Spark to unlock new ideas and experiment with large models (up to 200 billion parameters at FP4) directly on your desktop with 128GB of unified memory. Empower rapid testing, validation, and iteration—driving innovation in a secure, high-performance setting.
Check the index and tune search
Once indexing finishes, use Zoo Code’s codebase_search tool with a question tied to a real task, such as “How is user authentication handled?” The guide says results can include code snippets, file paths, line numbers, similarity scores, and navigation links. The Qdrant code-search tutorial provides additional context on semantic retrieval for code.
Zoo Code documents a default similarity-score threshold of 0.4. Treat it as a starting point: lowering the threshold can return more candidates with weaker relevance, while raising it tends to return fewer, more selective matches. Judge results against queries whose answers you can verify in the repository; there is no universally optimal threshold established by the documentation.
Rank #4
- 𝐏𝐨𝐰𝐞𝐫𝐟𝐮𝐥 & 𝐄𝐟𝐟𝐢𝐜𝐢𝐞𝐧𝐭 𝐏𝐞𝐫𝐟𝐨𝐫𝐦𝐚𝐧𝐜𝐞: Powered by the Intel Celeron J3355 Processor (up to 2.5GHz), this Mini PC delivers a 25% performance boost over previous generations. Pre-installed with Windows 11 Home and supporting Linux/Ubuntu, it’s the ideal micro desktop for seamless web browsing, document editing, and efficient daily office tasks.
- 𝐌𝐚𝐬𝐬𝐢𝐯𝐞 𝐒𝐭𝐨𝐫𝐚𝐠𝐞 & 𝐔𝐧𝐢𝐪𝐮𝐞 𝐄𝐱𝐩𝐚𝐧𝐬𝐢𝐨𝐧: Equipped with 6GB LPDDR3 RAM and 128GB onboard storage for fast boot-ups. Stand out with our dual M.2 SSD slot design (1x SATA + 1x NVMe), allowing you to easily expand storage up to 2TB without replacing the original drive. Perfect for managing large digital libraries and intensive multitasking.
- 𝐒𝐭𝐮𝐧𝐧𝐢𝐧𝐠 𝟒𝐊 𝐃𝐮𝐚𝐥 𝐇𝐃𝐌𝐈 𝐃𝐢𝐬𝐩𝐥𝐚𝐲: Boost your productivity with Intel HD Graphics 500 and dual HDMI ports, supporting 4K @60Hz high-definition visuals. Connect two monitors simultaneously to streamline your workflow—ideal for home office setups, stock trading, or enjoying a theater-like 4K media experience.
- 𝐔𝐥𝐭𝐫𝐚-𝐂𝐨𝐦𝐩𝐚𝐜𝐭 & 𝐒𝐩𝐚𝐜𝐞-𝐒𝐚𝐯𝐢𝐧𝐠 𝐃𝐞𝐬𝐢𝐠𝐧: Measuring only 4.2x4.1x1.4 inches and weighing just 0.49 lbs, this palm-sized mini computer fits anywhere. Use the included VESA bracket to mount it behind your monitor for a zero-clutter workspace. Features a smart silent fan and heat sink system for quiet, reliable 24/7 operation.
- 𝐒𝐭𝐚𝐛𝐥𝐞 𝐂𝐨𝐧𝐧𝐞𝐜𝐭𝐢𝐯𝐢𝐭𝐲 & 𝐒𝐦𝐚𝐫𝐭 𝐑𝐞𝐜𝐨𝐯𝐞𝐫𝐲: Stay connected with Dual-Band WiFi (2.4G/5G), Bluetooth 5.0, and Gigabit Ethernet. Exclusive One-Click Restore feature (via F9 key) allows for quick system recovery in minutes. Backed by Bmax's 12-month warranty and lifetime technical support for a worry-free purchase.
Understand speed and indexing limits
“Lightning-fast” is not a documented performance guarantee. The available documentation contains no controlled end-to-end measurement for Zoo Code, Ollama BGE-M3, and Qdrant, so it cannot establish indexing duration or search latency on a particular machine. Zoo Code notes that indexing may take time on large projects, including codebases with 10,000 or more files. Measure the experience on your own repository rather than inferring speed from model size or context window.
Zoo Code’s guide lists a maximum file size of 1 MB. Check the repository’s ignore rules if indexing is slow: the guide specifically recommends checking .gitignore and .rooignore patterns, since the files admitted to indexing affect the workload.
Best Value
- 【Powerful Ryzen 5 Processor】 The C4 Plus Mini PC is powered by the Ryzen 5 3501U processor (4 Cores/8 Threads, Base Clock 2.1GHz, Max Boost up to 3.7GHz) and features Radeon Vega 8 Graphics (1200MHz). Whether you're handling daily office tasks or streaming media, it delivers smooth and reliable desktop-class performance. Pre-installed 11 Pro OS .Support Ubuntu OS.
- 【Upgradable RAM & Storage】Comes pre-installed with 8GB DDR4 SODIMM RAM and a 256GB M.2 2280 SATA SSD for fast boot times and snappy application launches. Designed with flexibility in mind, it supports dual-channel memory expansion up to 32GB (SODIMM x2) and includes an extra slot for an M.2 2280 NVMe PCIe 3.0 x4 SSD, allowing you to effortlessly expand your storage capacity.
- 【Triple Display Video Output】Boost your productivity with support for up to three monitors simultaneously. This mini computer features versatile video output options including 1x HDMI 2.0 (4K@60Hz), 1x DisplayPort (4K@60Hz), and 1x USB Type-C (1080p@60Hz). It is the perfect multitasking solution for home offices, financial trading, or immersive home theater setups.
- 【Dual Gigabit LAN & Fast Connectivity】Built for robust networking with Dual RJ45 Gigabit Ethernet LAN ports, making it ideal for soft routing, homelab servers, or secure network configurations. It also features reliable wireless connectivity with M.2 Wi-Fi 5 (802.11ac) and Bluetooth 5.0, ensuring a stable connection for your wireless peripherals and internet browsing.
- 【Rich I/O Ports & Compact Design】Despite its space-saving footprint, the C4 Plus is packed with connectivity. It includes 3x ultra-fast USB 3.2 Gen 2 Type-A ports (10Gbps) for quick data transfers, 1x USB 2.0 port, and a 3.5mm combo audio jack. Package includes the Mini PC and a standard DC 19V/3.42A power adapter. Plug and play ready for your workspace.
Rebuild safely if the embedding model changes
BGE-M3 is listed by Ollama with 1024 embedding dimensions. Zoo Code warns that changing the vector dimension requires a full re-index. If the existing Qdrant collection contains vectors with a different dimension, use Zoo Code’s clear-index function before rebuilding. The guide says clearing deletes the Qdrant collection data and local file cache, and that the operation is irreversible.
Troubleshoot common problems
- Qdrant connection failure: Confirm Qdrant is running and that the URL in Zoo Code matches the local or cloud endpoint you intend to use.
- Slow indexing: Review
.gitignoreand.rooignorepatterns so unnecessary files are not included. Large projects can take longer to index. - Stuck or corrupted index: Zoo Code recommends clearing the index and indexing again. Clearing removes collection data and the local cache, so use it only when you are prepared to rebuild.
- Results seem incomplete: Confirm the files are within the documented 1 MB limit and that their languages are supported by Tree-sitter; Zoo Code says supported languages get the best results.
What about Roo Code and Cline?
The concrete setup above is documented for Zoo Code. A Lawrence Berkeley National Laboratory CBorg page’s search-result description associates Zoo Code with its former RooCode name, but that does not establish that all Roo releases have identical controls or indexing behavior. See CBorg’s Zoo Code page for that naming context.
The available evidence does not verify that current Cline builds provide this same built-in indexing panel and workflow. Do not assume the Zoo Code steps apply to Cline without checking the current documentation for the specific editor version you use.
Do these 3 things before closing this tab:
1Clear out junk files and repair common Windows errors2Scan for outdated or missing drivers - takes under a minute3Repair Windows errors before they cause bigger problemsQuick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
