Update README.md

README.md

@@ -36,13 +36,13 @@ BTW embedder is only a part of a good RAG<br>
 <br>
 <b>My short impression:</b>
 <ul style="line-height: 1;">
-<li>nomic-embed-text</li> 
+<li>nomic-embed-text (up to 2048t context length)</li> 
 <li>mxbai-embed-large</li>
 <li>mug-b-1.6</li>
-<li>snowflake-arctic-embed-l-v2.0</li>
-<li>Ger-RAG-BGE-M3 (german)</li>
+<li>snowflake-arctic-embed-l-v2.0 (up to 8192t context length)</li>
+<li>Ger-RAG-BGE-M3 (german, up to 8192t context length)</li>
 <li>german-roberta</li>
-<li>bge-m3</li> (up to 8192t context length)
+<li>bge-m3 (up to 8192t context length)</li>
 </ul>
 Working well, all other its up to you! Some models are very similar! (jina and qwen based not yet supported by LM)<br>
 With the same setting, these embedders found same 6-7 snippets out of 10 from a book. This means that only 3-4 snippets were different, but I didn't test it extensively.
@@ -84,7 +84,7 @@ This text snippet is then used for your answer. <br>
 <li>If, for example, the word “XYZ” occurs 100 times in one file, not all 100 are found.</li>
 <li>If only one snippet corresponds to your question all other snippets can negatively influence your answer because they do not fit the topic (usually 4 to 32 snippet are fine)</li>
 <li>If you expect multible search results in your docs try 16-snippets or more, if you expect only 2 than dont use more!</li>
-<li>If you use chunk-length ~1024t you receive more content, if you use ~256t you receive more facts.</li>
+<li>If you use chunk-length ~1024t you receive more content, if you use ~256t you receive more facts BUT lower chunk-length are more chunks and need much longer time.</li>
 <li>A question for "summary of the document" is most time not useful, if the document has an introduction or summaries its searching there if you have luck.</li>
 <li>If a book has a table of contents or a bibliography, I would delete these pages as they often contain relevant search terms but do not help answer your question.</li>
 <li>If the documents small like 10-20 Pages, its better you copy the whole text inside the prompt, some options called "pin".</li>
@@ -124,7 +124,7 @@ Your aim is to share delicious recipes, cooking tips and the stories behind diff
 ...
 <br>
 # usual models works well:<br>
-llama3.1, llama3.2, qwen2.5, deepseek-r1-distill, gemma-3, granit, SauerkrautLM-Nemo(german) ... <br>
+llama3.1, llama3.2, qwen2.5, deepseek-r1-distill, gemma-3, granite, SauerkrautLM-Nemo(german) ... <br>
 (llama3 or phi3.5 are not working well) <br><br>
 <b>&#x21e8;</b> best models for english and german:<br>
 granit3.2-8b (2b version also) - https://huggingface.co/ibm-research/granite-3.2-8b-instruct-GGUF<br>