yacy/defaults/web.xml, branch masterYaCy search server with some extra patches
https://git.fennell.dev/yacy/atom?h=master2026-07-04T11:01:38Zadded llm proxy servlet to augment the RAGProxyServlet with admin2026-07-04T11:01:38ZMichael Peter Christenmc@yacy.net2026-07-04T11:01:38Zurn:sha1:adb04ae3971ee8f976cc946c943e757a625cb558
access. We need this to do remote LLM inference configuration.added OpenAI models servlet and Ollama tags servlet2025-11-16T20:43:26ZMichael Peter Christenmc@yacy.net2025-11-16T20:43:26Zurn:sha1:bfdbcf58393b91dbbcf6dec713544480fea0b0faadded loging to MCP server2025-10-11T23:05:53ZMichael Peter Christenmc@yacy.net2025-10-11T23:05:53Zurn:sha1:02735a44a3f81d1b88231cb7e0d5fb81938f47e0added MCP server2025-10-10T23:28:55ZMichael Peter Christenmc@yacy.net2025-10-10T23:28:55Zurn:sha1:f41415a299ec5ac0f3797ee6f6a68faebbdc3940
You can now use YaCy as a search tool within an agentic LLM framework,
i.e. using MCP clients in N8N or OpenAI AgentBuilder.
The tool address is /tools
Added a RAG Proxy for AI Chat with YaCy2024-05-19T15:19:09ZMichael Peter Christenmc@yacy.net2024-05-19T15:19:09Zurn:sha1:13fbff0bffc78aa4676e92eb0ff95e5a9e98872f
RAG (Retrieval Augmented Generation) is a method to combine a search
engine with a LLM (Large Language Model). When a new prompt is
submitted, a search engine injects knowledge from a search into the
content. This is done using a reverse proxy between the Chat Client and
the LLM. In this case, we used the following software:
LLM Backend - Ollama:
https://github.com/ollama/ollama
Install ollama and then load two required LLM models
with the following commands:
ollama pull phi3:3.8b
ollama pull llama3:8b
Chat Client - susi_chat:
https://github.com/susiai/susi_chat
just clone the repository and the open the file
susi_chat/chat_terminal/index.html
in your browser. This displays a chat terminal.
In this terminal, run the following command:
host http://localhost:8090
This sets the LLM backend to your YaCy peer.
Then start YaCy. It will provide the LLM endpoint to the client
while using ollama in the backend. It then injects search results
only from the local Solr index, not from the p2p network (so far).
updated solr 6.6.6 -> 7.7.32020-12-12T01:06:43ZMichael Peter Christenmc@yacy.net2020-12-12T01:06:43Zurn:sha1:43a9f4f57446e6987cdb03f1fb7f17dd92f56b60
dropped GSA support (GSA API is still in YaCy Grid)
The 6.6.6 solr index works without migration also with 7.7.3extend the SolrServlet to be usable as remote solr (incl. update)2019-01-04T17:27:44Zsgaebelsgaebel@localhost2019-01-04T17:27:44Zurn:sha1:8f58c1dcfa557b88e665b7b30ac9b4fa790e5938
this feature needs to be enabled by uncomment the url-patternRemove deprecated YaCyProxyServlet2017-08-12T19:53:04Zregerreger18@arcor.de2017-08-12T19:53:04Zurn:sha1:b6a41df4f7e38ed93f510a437d112fcbb2951559
was replaced by UrlProxyServletmake digest default authentication in defaults/web.xml2017-03-15T00:39:15Zregerreger18@arcor.de2017-03-15T00:39:15Zurn:sha1:f7fce1baade428f1748414cd169e65359694ee45make Quality of Service Servlet available to prioritize requests from local host2015-04-26T02:29:32Zregerreger18@arcor.de2015-04-26T02:29:32Zurn:sha1:6bc8a9b11e0d54643edd65a82c3fb255d2a859c1
This assigns priorities to incoming requests. Higher priority numbers are served before lower.
(disabled by default in defaults/web.xml,
uncomment or copy entry to DATA/Settings/web.xml)