From 0adbc296929c99311a172ede72b095a8cc40f7d5 Mon Sep 17 00:00:00 2001
From: idchlife <idchlife@gmail.com>
Date: Thu, 5 Feb 2026 22:48:39 +0300
Subject: [PATCH] env step for llamaindex

---
 services/rag/.DS_Store              | Bin 6148 -> 8196 bytes
 services/rag/llamaindex/PLANNING.md |   9 ++++++++-
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/services/rag/.DS_Store b/services/rag/.DS_Store
index 163a714effbf83273caea88d0311b4fb012deac5..5bd78c607c9e3da706e2985d1f0f69fe1639eccb 100644
GIT binary patch
literal 8196
zcmeHMON<mn7_P5&fo^EoURY(o=`gTM5V9=G!|Z}!W?u>jEHJD)yCTcXbi3Qo+dWM8
z%<?i$OuVRIJZXG;(n#cBK#dnoR78)82aNGR)c82y!Hdelzq)z}?Biy9(Uo+4RrUXW
zRo7qN-<5xcF^0~vxrVU>V@#n(pgxDHDT<JbXHwzONDU##p0NTOVL4_q*YPK5#{;nk
zVh_X~h&>Q{Aojq&!2@(>i=s?(?@MW1#~z41a8r6fd>>Nu2uw#<l^A|Hs0vd6!de;*
z3$-Z^2yIdkrX#FM3{7cHnLQvfMU-Mdnv*;w)CtoORwYVv25HU^t&Au`LAW~Er9yRv
zw8XfMJrH|fvIj)&t}=(Rc9#ubpTAeS@{X5htR|B$I<_CQwtfX(Q#)hkEJd9?N4v%7
z&khV~`-b#+726u?Ee5vd`uAHUpKwU8^GCd~tp(5BRkDP<zu-CLQP&^R>kB!jP<C>G
z)!{f9`<O*zb$+4bInFN6x5YFA*}ysy2-zf2cF^}qL0350kgk_~YmY^9*%hmsX7sZ*
zEh!8eChQdInYjxVH{G#nZQG`F&(<BgFV^Yx^X4~b+MsP(ZeTxTTcy4++YCkqa(=;b
zP1_yruh_nwcdWf`Zq%wrv#MUKODtS;d(tqbQ_Yt1_TjP}9Mu~YC0rx5#L)Jc^m02q
zQ><d@=M<WUR$sQnFdh(+u98Ky85yitX=r<W+Jl~p6kAqn+TKI9YwEsu1u|W?UNicf
zT;6hYQ<dwqZ_teXiuAvJUo^P6K{K)iZ*-Kl=tpB6orbYrEW17D2fanhrB}KTt$h#4
z2K|v-$?6?*tx`0)jYh*GrEy`@W7>fi3dtKgX%_=xx(?F}_pm6ju+GRBeTx3MLPun~
z6+564qH`fA`%2^Z(KM!4%4XvShh!skwAz?%jZ_q7u(hn4ZD$8qi5+Jr*|Y34JIg+1
z=h>I+8}=i+!hQoV6Dnq74jQlsO=!lQXhS<TpcB2=jXlU<A4Xu~AbcFbF&xJUJch^d
zBu?TKp23TF8L!|~yn(lH7U%Fb-p2)eiqG%`F5_E#hwpI(zvB;F<umvKp5P1lQr^s0
z@fP03+xbR*7vITyd6wt+LGJOQe19I@RqVlNKN0Yw)R;QxiZbZ<nW=*=dGD63+qCWf
znV`EgSBBZGw=GC5Te*6D`{s^obd>xZr|k8C5VHS<m<ib*vSR{sFUok-7LUj3#K7#M
zu(6IPB6{^%QhTY^q)^!CGh}zUwnCwR(PzqTbFxLD5Y>6u)z&1}sT7EMjqElj+f+q|
z>}=FFsT7iWt?U|FT2*xxc9LDm9)-e6SN<x#Ut*Wp59}9qmH0jv^O3-Ev=Ynj#un@(
zo(q=uVLyhDLmnnZ;i8Dc#P}0<7>}TeNAUzP{uG|V(|8Wg;|08g*YG;A{xses&cB0q
z@g6?JM>vm9BKChx-2VwbPvG;88~Kc1r{;4dQ*s^89VY2`B;05i_x@22h`XOkLgfEF
z)BpY-D#caof!G88PY<BBJJa1sdz<bnEpqJ?JqPF!Md(!}h9*>n={RASjuT${!;so3
dQWZAo2&)olgv#IkLqIaV|Ks~Vq~1+k{RxZF{!ah^

delta 133
zcmZp1XfcprU|?W$DortDU=RQ@Ie-{MGqg=C6q~50D9Q+A12Ir6nIVHAks*^IuPk_C
zp*kbu=0LG+j2jz{vMy%l;1Fa6X#%R_1`@77+_tgsJM(0I8C_102?v0fVX_U6G!GNR
O4v@7Bo8x(AFarR^-xbgR

diff --git a/services/rag/llamaindex/PLANNING.md b/services/rag/llamaindex/PLANNING.md
index 1cad87a..55c5dc8 100644
--- a/services/rag/llamaindex/PLANNING.md
+++ b/services/rag/llamaindex/PLANNING.md
@@ -35,7 +35,14 @@ Chosen data folder: relatve ./../../../data - from the current folder
 
 - [x] Create file `retrieval.py` with the configuration for chosen RAG framework, that will retrieve data from the vector storage based on the query. Use retrieving library/plugin, that supports chosen vector storage within the chosen RAG framework. Retrieving configuration should search for the provided text in the query as argument in the function and return found information with the stored meta data, like paragraph, section, page etc. Important: if for chosen RAG framework, there is no need in separation of search, separation of retrieving from the chosen vector storage, this step may be skipped and marked done.
 
-# Phase 6 (chat feature, as agent, for usage in the cli)
+# Phase 6 (models strategy, loading env and update on using openai models)
+- [ ] Add `CHAT_STRATEGY`, `EMBEDDING_STRATEGY` fields to .env, possible values are "openai" or "ollama".
+- [ ] Add `OPENAI_CHAT_URL`, `OPENAI_CHAT_KEY`, `OPENAI_EMBEDDING_MODEL`, `OPENAI_EMBEDDING_BASE_URL`, `OPENAI_EMBEDDING_API_KEY` values to .env.dist with dummy values and to .env with dummy values.
+- [ ] Add in all important .env wise places in the code loading .env file for it's variables
+- [ ] Create reusable function, that will return configuration for models. It will check CHAT_STRATEGY and load environment variables accordingly, and return config for usage.
+- [ ] Add this function everywhere in the codebase where chat or embedding models configuration needed
+
+# Phase 7 (chat feature, as agent, for usage in the cli)
 
 - [ ] Create file `agent.py`, which will incorporate into itself agent, powered by the chat model. It should use integration with ollama, model specified in .env in property: OLLAMA_CHAT_MODEL
 - [ ] Integrate this agent with the existing solution for retrieving, with retrieval.py