Update README.md

README.md

@@ -28,6 +28,7 @@ architecture:
 <b> the setup for local documents described below is allmost the same, GPT4All has only one model (nomic)</b><br>
 
 (sometimes the results are more truthful if the “chat with document only” option is used)<br>
+BTW embedder is only a part of a good RAG<br>
 <b>&#x21e8;</b> give me a ❤️, if you like  ;)<br>
 <br>
 <b>My short impression:</b>
@@ -49,9 +50,10 @@ but in ALLM its cutting all in 1024 character parts, so aprox two times or bit m
 <br>
 
 -> Ok what that mean!<br>
+Your document will be embedd in x times 1024t Chunks(snippets),<br>
 You can receive 14-snippets a 1024t (14336t) from your document ~10000words and 1600t left for the answer ~1000words (2 pages)
 <br>
-You can play and set for your needs, eg 8-snippets a 2048t, or 28-snippets a 512t ...
+You can play and set for your needs, eg 8-snippets a 2048t, or 28-snippets a 512t ... (every time you change the chunk-length the document must be embedd again)
 <ul style="line-height: 1;">
 <li>8000t (~6000words) ~0.8GB VRAM usage</li>
 <li>16000t (~12000words) ~1.5GB VRAM usage</li>
@@ -80,7 +82,7 @@ This text snippet is then used for your answer. <br>
 
 <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 snipets-size ~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.</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>